Add repeatable --set key=value arguments and an --overrides <file.toml>
file to render_skill.py. Shipped defaults, project TOML, user TOML, the
invocation file, and command-line assignments resolve into one effective
customization using the existing structural merge; persistent files are
never written.
Two --set paths that are equal or nested halt as a caller error. The
renderer keeps no separate schema of customization keys: a --set path
must exist in customize.toml, and any invocation override that reaches
no token or condition halts. Values are validated where consumed.
Standalone [[bmad-if:path == literal]] / [[bmad-else]] / [[bmad-endif]]
lines select sections before token and link resolution. A secondary
file that filters to nothing is omitted from the snapshot; workflow.md
filtering to nothing is an error. Condition inputs join the generation
identity so identical output from different inputs still yields
distinct snapshots.
Document both interfaces, ignore the per-machine skills-lock.json, and
cover precedence, equivalent forms, isolation, conflicts, unused
overrides, malformed input, nested conditions, and snapshot reuse.
It wired Prettier and ESLint as save-time formatters and attached the
package.json schema; none of those exist at the root any more. The
rest was a 2025 spelling list and Copilot chat preferences. Nothing
reads the file. .vscode/ joins the ignored personal editor files so it
does not come back.
The root package.json, lockfile, .nvmrc, prettier ignore file and
.npmignore are gone. docs-site has its own package.json and lockfile
with the Astro, ESLint and Prettier dependencies, and its scripts run
relative to that directory. tools/quality.py, both workflows and the
docs all call npm inside docs-site.
stamp_release.py stamps only the 29 skill manifests now; the version
lives nowhere else on this branch. The tests for package stamping go
with it.
* build: declare the Python toolchain in pyproject.toml
Pin the dev environment (pytest, pytest-xdist, pyyaml, ruamel.yaml, ruff)
with uv instead of a one-line --with list in package.json. The project is
marked non-packaged: the tree itself is what gets installed, and shipped
scripts keep their inline metadata. The validate CI job now runs on uv
alone, without Node, and gains a ruff check.
* style: apply ruff to tools and skill scripts
Mechanical output of ruff check --fix and ruff format under the new
config, plus four hand edits: explicit zip strictness in setup.py and
test_sprint_status.py, an f-string for the hex colour in brain.py, and a
noqa on the sys.path-dependent import in render_skill.py. No behaviour
change; 500 tests pass.
* build: declare Python 3.11 as the floor of every shipped script
Eighteen scripts declared 3.8 or 3.10 inline while ruff targeted 3.11,
so an autofix could introduce syntax those scripts did not advertise.
The lower floors were never reachable: every skill that carried one
also runs a 3.11 hub script, and uv fetches whatever interpreter a
script asks for. All inline metadata now says 3.11, and a test keeps
the inline floors equal to requires-python and the ruff target.
Point both marketplaces at plugins/bmad-method. That folder holds the
host manifests and a skills/ symlink into the repo skills tree so an
install copies the plugin directory and Claude dereferences the payload.
Track the Codex catalog at .agents/plugins/marketplace.json.
* chore(review): swap Augment for Greptile and repair CodeRabbit config
Augment is no longer in use, so its guidelines file goes away in favour of
greptile.json. Rather than paraphrasing the repo's conventions, both bots are
now pointed at the same source files: AGENTS.md and tools/skill-validator.md,
plus docs/_STYLE_GUIDE.md scoped to docs.
Four CodeRabbit path instructions had gone stale and matched no tracked files:
src/**/skills/**, src/**/workflows/**, src/**/tasks/** and src/**/*.agent.yaml.
The skill-validator catalog was consequently applied to nothing. Retarget them
at src/*-skills/** and src/bmm-skills/agents/**, and drop the two describing
layouts the repo no longer has. Three further fixes: `walkthrough: false` is
not a schema v2 key, so use collapse_walkthrough; the media filters were
root-only globs and left docs/images under review; and the validation-report
filter named .md where those files are .html.
AGENTS.md gains the prompt-length and testing conventions, which were until
now written down nowhere in the repo. CLAUDE.md is unignored and imports it.
* chore(review): align catalog scoping and narrow the ignore lists
Greptile's global instructions named tools/skill-validator.md and
docs/_STYLE_GUIDE.md, but customContext.files supplies those only for skill and
documentation paths. Reviewing anything else, Greptile was told to apply
catalogs it had not been given — an invitation to invent rules from the
filenames. The global clause now names only AGENTS.md, which is loaded on every
review; the two scoped catalogs keep their scopes and their own descriptions.
website/** was excluding 18 hand-written source files along with the assets —
the Astro components and pages, both rehype plugins, the locale and site-url
helpers, the i18n JSON. Exclude website/public/** and website/diagrams/**
instead, so generated and editor-authored artifacts stay out while the source
is reviewed.
tools/tests/fixtures/** joins test/fixtures/** ahead of the validator port that
moves the skill fixtures there. Those fixtures encode defects deliberately, so
any review comment on them is wrong by construction.
* docs: create Build a Change page and retire Quick Fixes and Build
Consolidate how-to/quick-fixes and explanation/build into the canonical
build/build-a-change page, opening with the sizing model and Where Build
Fits table and preserving the Build diagram and intent examples. Add the
Build sidebar group after Start, redirect both old routes, retarget
first-party English links and the llms.txt entry, and close the resulting
sidebar-order gaps.
* fix(docs): track Build a Change page by scoping Astro build ignore
The bare build/ gitignore rule also matched docs/build/, so the new
canonical page never entered the prior commit.
* docs: rewrite Build a Change page in plain English
Name the skill as bmad-build instead of Build, drop the duplicated
routing tables, and explain why it spends human attention on a few
checkpoints instead of a Continue slog.
* feat(party-mode): add persistent per-party memory
Each party now keeps a succinct, append-only memlog (the memlog standard)
under {memory_dir}/<party>/, so a room remembers prior sessions and opens
in character carrying them forward.
- Memory accrues live: capture memorable beats as they land, with a floor
so an abandoned session still leaves a trace; wrap-up is a top-up.
- Read distills via a reader subagent that returns only current standing
state (latest dynamic per pair, open threads, recent callbacks) so the
raw log never enters the party context.
- Writes are silent and fail safe: a missing or erroring memlog.py is
skipped without breaking the fiction.
- New customize knobs: party_memory (on by default) and memory_dir.
Keyed per party (group id, or `installed` for the default room); ad-hoc
casts stay ephemeral. On-disk compaction is left to a future memlog.py pass.
* refactor(party-mode): standard structure, per-group memory, keep on-the-fly cast
- Restructure SKILL.md to the standard skill shape (intro -> Conventions ->
On Activation -> content); consolidate all performance rules into one
"Keep It Feeling Like a Party" section. SKILL.md ~500 tokens lighter.
- Per-group `memory` flag: global party_memory now governs only the default
room; resolve_party.py resolves memory_enabled per active roster (default
room -> party_memory, named group -> own flag), with tests.
- On-the-fly characters are captured as memlog entries during a session; at
wrap-up the room offers to save them into the party via bmad-customize.
- Memory mechanics consolidated into references/party-memory.md; SKILL.md
step 5 just routes to it.
- Docs updated.
* docs(party-mode): fix open-cast lock-down claim and python3->uv run in create-party
* Rework solutioning architecture skill into bmad-architecture (spine)
- Rename canonical skill bmad-tech-plan -> bmad-architecture; output is ARCHITECTURE-SPINE.md
- Convert bmad-create-architecture to a deprecated husk forwarding to bmad-architecture (create intent); strip steps/data/template
- Finalize: spine is the default, then offers fuller renderings + a self-contained HTML view; doc_standards polish applies to prose docs only
- Reviewer Gate: add adversarial divergence-hunter, on by default at high/regulated/cross-team stakes
- Fix references in module-help.csv, bmad-prd, bmad-ux, bmad-agent-architect; reword help entry for when-to-offer
- bmad-spec: flag recognized-but-unaddressed domain implications as open_questions
* bmad-architecture: extract Finalize/reviewer-menu to references, add grade_spine script
- Move the Finalize sequence out of SKILL.md into references/finalize.md
- Make references/validate.md own the canonical reviewer menu and prompts
- Add scripts/grade_spine.py (+ tests) so validation grade is computed
deterministically instead of derived by hand
- Tighten SKILL.md spine/memlog framing
* bmad-architecture: outcome-driven rewrite + spawned reviewer gate
Re-express SKILL.md as goals/outcomes rather than procedure: intent is read
from the input (raw idea, large doc, codebase, feature slice, existing spine)
instead of a Create/Update/Validate x mode matrix. Restore the counter-default
coaching invariants that over-compression had stripped — Guided is the default,
load-bearing calls are shown with alternatives and the user chooses, recommend a
known starter when the stack is open, investigate brownfield before deciding.
Adopt the bmad-prd/product-brief shape: a dedicated Reviewer Gate that always
spawns finalize_reviewers as parallel subagents against the spine (lint floor
first; ad-hoc lenses scaled to rigor/altitude/criticality), and a numbered
Finalize that calls it. Headless runs the full gate non-interactively.
Reframe the structural seed as the living source of truth for shape (code owns
detail; evolve on shape change; memlog keeps history). Fix template mermaid
(C4 -> flowchart, valid one-attr-per-line erDiagram). Ship two default
finalize_reviewers (currency/reality check, adversarial divergence hunter).
Remove grade_spine.py and the inlined discovery/inputs/validate/finalize refs.
* bmad-architecture: review fixes — shared memlog, epic altitude, lint hardening
Pre-PR review fixes for the new architecture-spine skill:
- Adopt the shared canonical memlog (#2462); drop the vendored copy and the
status-flag lifecycle in favor of `event` entries
- Wire epic-altitude inheritance: parent-spine load+bind, Inherited Invariants
template section, epic-scoped run folder, parent-contradiction lens; state
that per-story detail is deferred to bmad-create-story
- Add the Update intent; honor a forwarded-activation handoff from the
deprecated bmad-create-architecture shim
- Rename modes to Coaching path / Fast path (suite-consistent with prd/brief)
and sequence the offer as an activation step
- Fix the brownfield project-context.md default path ({output_folder} no-op)
- lint_spine: line-exact frontmatter, fence-blanking (AD-in-fence + accurate
line numbers), map-form key_deps, AD-0 fix; soften template-token severity;
add 8 tests
- Carve the Reviewer Gate to references/ to stay under the SKILL.md token budget
- Template: entities-only ERD, scale-down guidance, softened seed framing;
gitignore .memlog.md
* bmad-architecture: address PR review (augment + coderabbit)
- REF-03: use canonical "invoke the `skill` skill" language for all cross-skill
references in SKILL.md (was "route to / offer / hand to / Next:")
- lint_spine: scan frontmatter for unfilled template tokens / TBD (paradigm,
scope, date were uncatchable in the body-only pass)
- lint_spine: guard read_text() so a bad-encoding/unreadable spine returns error
JSON and exit 0, honoring the documented contract
- reviewer-gate: resolve the "always run" vs "may skip" ambiguity — the gate
scales/skips by stakes, but finalize_reviewers always run once it does
- tests: +3 (frontmatter token, frontmatter TBD, unreadable spine); use next()
* bmad-architecture: align finalize-reviewers wording + headless blocked output
- customize.toml: reword finalize_reviewers comment to match reviewer-gate.md —
the gate is stakes-gated, but its reviewers always run once it does (coderabbit)
- headless.md: state explicitly that a blocked run omits spine/memlog/companions,
matching the "omit keys for artifacts not produced" contract (coderabbit)
* bmad-architecture: ask deliverable purpose up front, offer presentable renderings, lead next-steps with bmad-spec
* feat(web-bundles): add release packager + bundle manifest
Adds the infrastructure for shipping web bundles as downloadable ZIPs
attached to a GitHub Release, consumed by the upcoming
bmadcode.com/web-bundles/ page.
- web-bundles/bundles.json — manifest with persona, tagline, description,
accent color, motif key, knowledge files, and feature flags
(web-browsing, deep-research, stitch integration) for each of the 6
bundles. Top-level releaseTag and downloadUrlPattern so the
consuming page can construct download URLs without hardcoding.
- tools/bundle-web-bundles.js — packager that zips each bundle dir into
dist/web-bundles/{slug}.zip and prints the gh release create command.
Zero dependencies; uses system zip.
- .gitignore — exclude dist/web-bundles/ build artifacts.
The web-bundles-v1.0.0 release on GitHub is currently in draft state
with the 6 zips attached; it'll be published in coordination with the
Ghost site page going live.
* fix(web-bundles): single-source release tag, sharper bundle copy
- Remove downloadUrlPattern from bundles.json — the consuming page
derives the URL from releaseTag, so version bumps now touch one
field instead of two.
- product-brief-coach: drop "one-page" (briefs are whatever length
the product earns).
- brainstorming-coach: real numbers — 60 techniques across 10
categories — with concrete examples (SCAMPER, Drunk History
Retelling, Nature's Solutions, Six Thinking Hats, etc.) so the
card actually communicates the surprising breadth.
* fix(web-bundles): harden release script per PR review
- Verify the zip CLI is on PATH up front with a clear install
hint, instead of crashing mid-zip with an opaque execSync error.
- Wrap JSON.parse in try/catch; validate the manifest shape (bundles
array non-empty, releaseTag present, slug present per entry) before
trying to package, so config errors fail with a targeted message.
- Catch zip failures per-bundle and surface the failing slug.
- Refuse to print the gh release command when zero bundles were
packaged (would otherwise mislead the user into creating an empty
release).
- Derive --title from manifest.releaseTag so the printed command can
never drift from the actual tag (was previously hardcoded
"Web Bundles v1" while the tag had moved to v1.0.0).
- Remove the stale `web-bundles-v1` example from the file header.
Addresses augmentcode bot review comments on PR #2424.
* docs(web-bundles): rewrite copy to actually sell what each bundle does
The JSON drives the bmadcode.com/web-bundles/ page; previous copy
was generic and undersold the actual capabilities. Rewrote each
tagline + description to lead with concrete, differentiating facts
pulled directly from each bundle's SKILL.md:
- Brainstorming Coach: 60 techniques across 10 categories with
specific names (SCAMPER, Drunk History Retelling, Nature's
Solutions, Shadow Work Mining, Superposition Collapse); calls
out the 4 routes (browse, recommend, random, progressive) and
the ~100-idea quantity-unlocks-quality target.
- Product Brief Coach: names the three intent modes (Create /
Update / Validate) and the two working paths (Fast / Coaching);
surfaces the [ASSUMPTION] tag system and the Addendum.
- PRFAQ Coach: details the 4 stages (Ignition / Press Release /
Customer FAQ / Internal FAQ + Verdict), the 9 press release
sections, the weasel-word list ("best-in-class", "seamless"),
and that it adapts for commercial, internal, OSS, community.
- PRD Coach: spells out the two entry points (Vision+Features
vs Journey-led), named-protagonist journeys, glossary
discipline, stable ID system (FR-1..N, SM-C1..N), and the
7-dimension validation rubric.
- UX Coach: leads with the two-spine contract (DESIGN.md +
EXPERIENCE.md), Don Norman framing, named-protagonist
journeys, surface closure as the test, and Stitch integration.
- Market & Industry Research: leads with Deep Research as the
engine, names Porter and Christensen as anchors, lists the 6
deliverable sections, and frames the deliverable as synthesis
not a research dump.
* fix(web-bundles): security hardening + strict bundle validation
Two issues raised by coderabbit on the latest commit:
1. Shell injection surface: execSync was building the zip command
with a template literal that interpolated bundle.slug from JSON.
Even with our controlled inputs, a slug with shell metacharacters
would break quoting. Switched to execFileSync with an argument
array (no shell) and added a strict ^[a-z0-9][a-z0-9-]*$ slug
regex enforced before any FS or zip call.
2. Missing bundle directories were [SKIP]-warned but the script
still printed the release command, allowing an incomplete release
to ship cleanly. Now treated as fatal: any missing or invalid slug
blocks the printed gh command and exits non-zero with the offending
slugs listed.
* feat(skills): TOML-based agent customization with stdlib Python resolver
Re-applies PR #2282's three-layer customization model (skill defaults →
team → user) but swaps YAML for TOML and uv for stdlib tomllib. Users
no longer need uv, pip, or a virtualenv — plain python3 (3.11+) is
sufficient, since tomllib shipped in the standard library.
## Schema changes vs PR #2282
- Flat agent schema: fields live directly under [agent], no nested
metadata/persona sub-tables. Easier to author, less indentation.
- Non-configurable identity: name and title are declared in
customize.toml as source-of-truth metadata (for future skill-manifest
generation) but SKILL.md ignores overrides there — identity is
hardcoded to preserve brand recognition.
- role redefined: now describes what the skill does for the user
within its module phase, not a restatement of the title.
- persistent_facts replaces the activation-time file-context load AND
the old memories concept. Entries can be literal sentences or
file: prefixed paths/globs; avoids collision with the upcoming
runtime memory sidecar.
- activation_steps_prepend / activation_steps_append harmonized across
agents and workflows (replaces agent-specific critical_actions).
- [workflow] namespace mirrors [agent] for workflow customization.
Same four structural rules, same field vocabulary.
## Resolver (src/scripts/resolve_customization.py)
Four purely structural merge rules, zero field-name hardcoding:
- Scalars: override wins
- Tables: deep merge
- Arrays of tables where every item has `code` or `id`: merge by
that key (matching keys replace, new keys append)
- Any other array: append
No removal mechanism — overrides cannot delete base items. Fork the
skill or override by code with a no-op value to suppress defaults.
## Agents ported (6)
All six BMad agents now ship customize.toml + rewritten SKILL.md:
analyst (Mary), tech-writer (Paige), pm (John), ux-designer (Sally),
architect (Winston), dev (Amelia). Each uses the same 8-step
activation template: resolve → execute prepend → adopt persona →
load persistent facts → load config → greet (with {agent.icon}) →
execute append → dispatch or present menu.
Step 8 supports fast-path invocation: "hey Mary, let's brainstorm"
dispatches the matching menu item directly after greeting, skipping
the menu render when intent is clear. Chat, clarifying questions,
and bmad-help remain available when nothing on the menu fits.
## Installer + tooling
- _bmad/scripts/ provisioned on install (copies src/scripts/)
- _bmad/custom/ seeded with .gitignore for *.user.toml on fresh install
- Non-module-dir filter extended to skip _memory, memory, docs,
scripts, and custom when scanning for modules
- Dead _config/agents/ directory no longer created
- metadata.capabilities removed from agent-manifest.csv and schema
- eslint config extended to cover src/scripts/**
- validate-file-refs.js knows about custom/ as install-only
## Deferred for follow-up
- bmad-product-brief workflow port (the pilot that demonstrates
[workflow] + on_complete)
- Translated docs (cs/fr/vi-vn/zh-cn) — regenerate from English
* feat(skills): port bmad-product-brief to TOML workflow customization
Completes the customization surface rollout by giving the product-brief
workflow the same override model as the six BMad agents, under the
[workflow] namespace instead of [agent].
## customize.toml
Mirrors the agent shape under [workflow] with:
- activation_steps_prepend / activation_steps_append (harmonized across
agents and workflows — same field names, same append semantics)
- persistent_facts with the file: convention, seeded with
file:{project-root}/**/project-context.md
- on_complete scalar (renamed from PR #2282's skill_end for clarity —
reads cleaner as "what runs when the workflow completes")
## SKILL.md
7-step workflow activation:
1. Resolve workflow block
2. Execute prepend steps
3. Load persistent facts (file: or literal)
4. Load config
5. Greet if not already
6. Execute append steps
7. Stage 1 — Understand Intent
python3 + stdlib tomllib invocation; no uv required.
## Prompt file changes
- Path normalization: ../agents/ → agents/, ../resources/ → resources/,
bare foo.md → prompts/foo.md. All references now resolve from the
skill root (matches the convention documented in SKILL.md).
- Paths: meta-line added to each of the 4 prompt files that reference
other files, reinforcing "bare paths resolve from skill root" so the
LLM doesn't lose the convention when operating two hops into a
prompt chain.
- finalize.md terminal stage now calls the resolver for
workflow.on_complete — non-empty values run as the final step.
## Validation
- Resolver output verified: 4 workflow fields returned cleanly.
- validate-file-refs.js: 254 files scanned, 139 refs checked, 0 broken.
- test:refs: passing.
* docs(skills): enterprise customization recipes + workflow template variable
Three independent improvements bundled because they share the same
surface (workflow/agent customization) and landed from the same design
discussion:
## Fallback sentence disambiguated (7 SKILL.md files)
The "if the script fails" fallback used to say `{project-root}/_bmad/
custom/{skill-name}.toml` for the team override and then just `{skill-
name}.user.toml` for the user override, leaving the user file's
location implicit. LLMs could reasonably guess skill root or project
root instead. Replaced with an unambiguous numbered list that spells
out the full path for every file in the merge chain.
## Product-brief: stage promotion + brief_template variable
- Promoted `## Stage 1: Understand Intent` from a nested step inside
"On Activation" to a top-level section. The previous "Step 7: Stage
1 — Understand Intent → Proceed to Stage 1 below" was mechanical
numbering pretending to be a step. Activation now ends cleanly at
Step 6; Stage 1 is a peer section.
- Added `brief_template` as a workflow-level scalar customization
defaulting to `resources/brief-template.md`. Stage 4 reads
`{workflow.brief_template}` instead of the hardcoded path, so orgs
can point at their own template under `{project-root}/...` without
forking the skill.
## New doc: docs/how-to/extend-bmad-for-your-org.md
Four worked recipes that together cover most enterprise scenarios:
1. Shape an agent across every workflow it dispatches (dev agent +
Context7 MCP + Linear search — the highest-leverage pattern)
2. Enforce org conventions inside a specific workflow (product-brief
+ compliance-field persistent_facts)
3. Publish completed outputs to external systems (product-brief +
Confluence + Jira via MCP, gated on user confirmation for Jira)
4. Swap in your own output template (product-brief + brief_template
variable swap)
Opens with the two-layer mental model (agent spans workflows,
workflow is local) so readers pick the right granularity before
reading any recipe. Closes with a "Combining Recipes" section
showing all four composed. Cross-linked from customize-bmad.md.
## Validation
- Resolver: workflow.brief_template returns the default cleanly.
- validate-file-refs.js: 254 files scanned, 146 refs checked
(+7 from this commit), 0 broken.
* docs(skills): encourage CLAUDE.md/AGENTS.md reinforcement of critical rules
Added a "Reinforce Global Rules in Your IDE's Session File" section to
extend-bmad-for-your-org.md. BMad customizations only load when a
skill activates, but IDE session files (CLAUDE.md, AGENTS.md, cursor
rules, copilot-instructions) load every turn — worth restating the
most critical rules there too so they survive ad-hoc chat outside a
BMad skill.
Includes a one-line example reinforcing the Recipe 1 Context7 rule,
plus a scope table that clarifies what each layer is for:
- IDE session file: universal, every session, keep succinct
- Agent customization: persona-specific, every dispatched workflow
- Workflow customization: one workflow run
Emphasizes brevity — noise in the session file crowds out signal.
* docs(skills): add Named Agents explanation doc
New docs/explanation/named-agents.md walking through the three-legged
stool (skills + named agents + customization) with the "Hey Mary,
let's brainstorm" activation flow as the narrative thread.
Covers:
- Why named agents vs menu-driven or prompt-driven alternatives
- The 8-step activation flow and what each step contributes
- How customization scales the model beyond a single developer
- Cross-links to the how-to docs for implementation details
Sits alongside brainstorming.md, quick-dev.md, party-mode.md in the
explanation folder — feature narratives for users who want to
understand why BMad is designed the way it is, not just how to use it.
* docs(skills): clarify that keyed-merge requires a single identifier key per array
Review feedback (PR #2284) flagged that the merge-rules wording was
ambiguous: "every item has a `code` or `id` field" could reasonably
be read as "each item individually has at least one of the two",
allowing arrays to mix `code` and `id` across items.
The resolver has always required all items share the *same* identifier
key (all `code`, or all `id`). Mixed arrays fall through to append —
intentional, because mixing identifier keys within one array is a
schema smell and any guess about which key should merge creates a
worse trap than the append-fallback.
Clarified in three places:
- Merge-rules table in customize-bmad.md: "every item shares the
**same** identifier field"
- `code`/`id` convention paragraph: "pick **one** convention ... and
stick with it across the whole array"
- Resolver docstring and `_detect_keyed_merge_field` docstring:
explicit note that mixed arrays fall through with rationale
No behavior change.
* docs(skills): address CodeRabbit review — fallback rules, OS claim, headless greeting
Three fixes from PR #2284 review feedback:
## 1. Fallback merge wording (7 SKILL.md files)
Every SKILL.md told the LLM to merge the three customization files
"in priority order (later wins)" when the resolver fails. That reads
as shallow last-write-wins — but the resolver does structural merge
(scalars override, tables deep-merge, code/id-keyed arrays merge by
key, other arrays append). Following the old wording manually would
have silently stripped base `principles`, `persistent_facts`, and
`menu` items whenever a team override was present.
Expanded the fallback sentence to restate the four structural rules
explicitly, matching the resolver's behavior.
Applied to all 6 agents + bmad-product-brief workflow.
## 2. Python 3.11 / OS shipping claim (customize-bmad.md)
The docs claimed "macOS 13+, Ubuntu 22.04+, Debian 12+, Fedora 37+
all ship 3.11 or newer." Inaccurate — Ubuntu 22.04 defaults `python3`
to 3.10.6 (3.11 is a separate package), and macOS doesn't really
ship Python by default anymore.
Replaced with honest guidance: check `python3 --version` and note
that macOS without Homebrew and Ubuntu 22.04 default to 3.10 or
earlier.
## 3. Autonomous mode greeting gate (bmad-product-brief)
Product-brief's activation-mode detection documents autonomous mode
as "produce complete brief without interaction" — but Step 5 greeted
unconditionally, adding conversational output before the headless
artifact. Gated the greeting on `{mode}` != `autonomous`.
## Dismissed (replied on thread)
- `.gitignore` migration from *.user.yaml to *.user.toml: YAML
installer code was in reverted #2282, never released. No users
affected. Same rationale as Augment's earlier thread.
Validated: 254 files, 146 refs, 0 broken. test:refs 7/7,
test:install 242/242.
* docs: rename Extend to Expand throughout customization docs
Three-layer customization (skill defaults → team → user) for BMad agents
and any skill that opts in. Users edit `_bmad/custom/{skill-name}.yaml`
(team, committed) or `{skill-name}.user.yaml` (personal, gitignored);
customizations survive updates.
Resolver is a Python script using PEP 723 inline metadata, invoked via
`uv run` so deps auto-install into a cached isolated env on first call.
This aligns with Anthropic's Agent Skills spec and BMB conventions, and
keeps the dependency declared (scannable by pip-audit/Dependabot) rather
than vendored.
## Design choices
- **Agent identity is hardcoded** in SKILL.md (name, title, Overview prose)
so skills can be invoked reliably by role *or* default name. Brand
recognition is preserved; customization shapes behavior, not identity.
- **Luminary-anchored personas** (e.g. "Channels Martin Fowler's
pragmatism and Werner Vogels's cloud-scale realism") deliver ~55%
token savings per agent while preserving distinctive voice beats.
- **Universal per-field merge rules** with v6.1-compatible agent
semantics: metadata shallow-merge, persona replace, critical_actions
and memories append, menu merge-by-code, all else deep-merge.
- **Workflow customization** shares the same surface — `bmad-product-brief`
pilots `activation_steps_prepend`, `activation_steps_append`, and
`skill_end` hooks that any workflow-style skill can adopt.
## Infrastructure
- `_bmad/scripts/` houses shared Python scripts (resolver + future).
- `_bmad/custom/` is provisioned empty with a seeded `.gitignore` for
`*.user.yaml` on fresh installs.
- Installer filters ensure `scripts/`, `custom/`, and sidecar-generated
`memory/` directories are never treated as modules.
- Dead v6.1 code cleaned up: `_config/agents/` no longer created,
`metadata.capabilities` removed from schema and CSV manifest.
* feat(i18n): add zh-cn locale support with Starlight routing
Reorganize Chinese translations from docs_cn/ into docs/zh-cn/
following Starlight's i18n content structure. Configure Starlight
with root locale (en, unprefixed) and zh-cn (/zh-cn/ prefix).
- Move 28 files from docs_cn/*_cn.md to docs/zh-cn/*.md
- Fix 21 internal links to remove _cn suffixes
- Add defaultLocale + locales config to astro.config.mjs
- Add .gitignore exception for docs/zh-cn/ (overrides z*/ rule)
- Language switcher activates automatically via existing Header
- hreflang tags auto-generated by Starlight on all pages
* feat(i18n): add zh-CN UI translations and sidebar labels
- Add website/src/content/i18n/zh-CN.json with Starlight UI strings
- Add sidebar group label translations (欢迎, 路线图, 教程, etc.)
- Register i18n collection in content config to fix deprecation warning
* fix(i18n): exclude 404 pages from sitemap
Custom 404 pages (root and zh-cn) were indexed as regular content in
the sitemap. Add a filter to the @astrojs/sitemap integration that
matches the /404 path segment precisely via regex on the URL pathname.
* feat: migrate Codex installer from .codex/prompts to .agents/skills format
Switch CodexSetup to write BMAD artifacts as Agent Skills (agentskills.io
format) in .agents/skills/<name>/SKILL.md instead of flat files in
.codex/prompts. Remove global/project location prompt. Add legacy cleanup
of old .codex/prompts directories during install and uninstall.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* ignore .agents for codex
* fix: normalize line endings and use platform-native EOL in SKILL.md output
Normalize all content to LF in transformToSkillFormat, then convert to
os.EOL (CRLF on Windows, LF on Linux/macOS) before writing SKILL.md
files in both writeSkillArtifacts and installCustomAgentLauncher.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* ignore .agents directory
* use description from metadata in custom agent launcher
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add CodeBuddy (Tencent Cloud Code Assistant) as a supported IDE platform:
- Add platform config to tools/platform-codes.yaml
- Add installer config to tools/cli/installers/lib/ide/platform-codes.yaml
- Add .codebuddy to .gitignore
CodeBuddy uses the default template type with target directory .codebuddy/commands
Co-authored-by: wison <wisonlin@tencent.com>
Co-authored-by: Brian <bmadcode@gmail.com>
Add Augment Code Review (audit mode) and CodeRabbit (adversarial mode):
Augment (.augment/code_review_guidelines.yaml):
- Workflow structure and step validation rules
- Agent definition validation
- Path placeholder enforcement
- JIT loading and HALT requirements
CodeRabbit (.coderabbit.yaml):
- Raven-style adversarial reviewer persona
- Finds logical contradictions and missing implementations
- No rule anchoring - reasons freely
Supporting changes:
- .gitignore: exclude .augment/ from ignore
- eslint.config.mjs: ignore .augment/ directory
fix: clarify .augment gitignore pattern and eslint comment
Add documentation comment to .gitignore explaining the .augment/*
exception pattern, and replace misleading eslint comment about
"underscores per their spec" with accurate description of vendor
config directory exclusion.
Addresses CodeRabbit findings F10 and F11 from PR #1511 review.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fix: remove redundant eslint ignore patterns
The broader glob patterns (dir/**) already match all files recursively,
making the more specific sub-patterns (dir/**/*.js, dir/**/*.md, etc.)
completely redundant. Similarly, _bmad*/** already covers _bmad/**.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fix: synchronize ignore baselines across CodeRabbit and Augment configs
Expand path exclusions in both PR review tools to a shared baseline:
- Mutual config exclusions (each tool ignores its own and others configs)
- Build output, vendored/generated files, package metadata, binary/media
- Test fixtures, non-project dirs, AI assistant dirs, build temp
- Generated reports
CodeRabbit goes from 1 exclusion to 32; Augment from 12 to 32.
ESLint already had comprehensive ignores and is unchanged.
Addresses CodeRabbit findings F2 and F4 from PR #1511 review.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fix: correct project name in Augment review guidelines
fix: remove instruction that explicitly encourages false positives
Replace ambiguous "execute" terminology with explicit "Read fully and follow:"
phrasing across all workflow files to prevent LLM goal-seeking behavior where
models attempt to "achieve the end result" rather than following step-by-step
instructions verbatim.
Changes:
- Update 5 handler templates with canonical phrasing
- Replace ~150 INSTRUCTIONAL patterns across 87 workflow files
- Add "[Workflow] complete." prefix to 7 workflow endpoints
- Preserve BEHAVIORAL/STRUCTURAL patterns (agent descriptions, XML tags)
- Fix gitignore and markdownlint to ignore all node_modules directories
Closes#1372
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: web bundler entry point
* removed the web-bundles folder
* added web-bundles to gitignore
* disabled web bundles
---------
Co-authored-by: Brian <bmadcode@gmail.com>
* feat(docs): add Diataxis folder structure and update sidebar styling
- Create tutorials, how-to, explanation, reference directories with subdirectories
- Add index.md files for each main Diataxis section
- Update homepage with Diataxis card navigation layout
- Implement clean React Native-inspired sidebar styling
- Convert sidebar to autogenerated for both Diataxis and legacy sections
- Update docusaurus config with dark mode default and navbar changes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(docs): migrate Phase 1 files to Diataxis structure
Move 21 files to new locations:
- Tutorials: quick-start guides, agent creation guide
- How-To: installation, customization, workflows
- Explanation: core concepts, features, game-dev, builder
- Reference: merged glossary from BMM and BMGD
Also:
- Copy images to new locations
- Update internal links via migration script (73 links updated)
- Build verified successfully
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(docs): add category labels for sidebar folders
Add _category_.json files to control display labels and position
for autogenerated sidebar categories.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* style(docs): improve welcome page and visual styling
- Rewrite index.md with React Native-inspired welcoming layout
- Add Diataxis section cards with descriptions
- Remove sidebar separator, add spacing instead
- Increase navbar padding with responsive breakpoints
- Add rounded admonitions without left border bar
- Use system font stack for better readability
- Add lighter chevron styling in sidebar
- Constrain max-width to 1600px for wide viewports
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: use baseUrl in meta tag paths for correct deployment URLs
* feat(docs): complete Phase 2 - split files and fix broken links
Phase 2 of Diataxis migration:
- Split 16 large legacy files into 42+ focused documents
- Created FAQ section with 7 topic-specific files
- Created brownfield how-to guides (3 files)
- Created workflow how-to guides (15+ files)
- Created architecture explanation files (3 files)
- Created TEA/testing explanation files
- Moved remaining legacy module files to proper Diataxis locations
Link fixes:
- Fixed ~50 broken internal links across documentation
- Updated relative paths for new file locations
- Created missing index files for installation, advanced tutorials
- Simplified TOC anchors to fix Docusaurus warnings
Cleanup:
- Removed legacy sidebar entries for deleted folders
- Deleted duplicate and empty placeholder files
- Moved workflow diagram assets to tutorials/images
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(build): use file glob instead of sidebar parsing for llms-full.txt
Replace brittle sidebar.js regex parsing with recursive file glob.
The old approach captured non-file strings like 'autogenerated' and
category labels, resulting in only 5 files being processed.
Now correctly processes all 86+ markdown files (~95k tokens).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(seo): use absolute URLs in AI meta tags for agent discoverability
AI web-browsing agents couldn't follow relative paths in meta tags due to
URL security restrictions. Changed llms-full.txt and llms.txt meta tag
URLs from relative (baseUrl) to absolute (urlParts.origin + baseUrl).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(docs): recategorize misplaced files per Diataxis analysis
Phase 2.5 categorization fixes based on post-migration analysis:
Moved to correct Diataxis categories:
- tutorials/installation.md → deleted (duplicate of how-to/install-bmad.md)
- tutorials/brownfield-onboarding.md → how-to/brownfield/index.md
- reference/faq/* (8 files) → explanation/faq/
- reference/agents/barry-quick-flow.md → explanation/agents/
- reference/agents/bmgd-agents.md → explanation/game-dev/agents.md
Created:
- explanation/agents/index.md
Fixed all broken internal links (14 total)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(docs): add Getting Started tutorial and simplify build script
- Add comprehensive Getting Started tutorial with installation as Step 1
- Simplify build-docs.js to read directly from docs/ (no consolidation)
- Remove backup/restore dance that could corrupt docs folder on build failure
- Remove ~150 lines of unused consolidation code
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(css): use fixed width layout to prevent content shifting
Apply React Native docs approach: set both width and max-width at
largest breakpoint (1400px) so content area maintains consistent
size regardless of content length. Switches to fluid 100% below
1416px breakpoint.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(docs): restructure tutorials with renamed entry point
- Rename index.md to bmad-tutorial.md for clearer navigation
- Remove redundant tutorials/index.md
- Update sidebar and config references
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(docs): add tutorial style guide and AI agent announcement bar
- Add docs/_contributing/ with tutorial style guide
- Reformat quick-start-bmm.md and bmad-tutorial.md per style guide
- Remove horizontal separators, add strategic admonitions
- Add persistent announcement bar for AI agents directing to llms-full.txt
- Fix footer broken link to tutorials
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(docs): add markdown demo page and UI refinements
- Add comprehensive markdown-demo.md for style testing
- Remove doc category links from navbar (use sidebar instead)
- Remove card buttons from welcome page
- Add dark mode styling for announcement bar
- Clean up index.md card layout
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(docs): apply unified tutorial style and update references
- Reformat create-custom-agent.md to follow tutorial style guide
- Update tutorial-style.md with complete unified structure
- Update all internal references to renamed tutorial files
- Remove obsolete advanced/index.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(docs): migrate from Docusaurus to Astro+Starlight
Replace Docusaurus with Astro and the Starlight documentation theme
for improved performance, better customization, and modern tooling.
Build pipeline changes:
- New build-docs.js orchestrates link checking, artifact generation,
and Astro build in sequence
- Add check-doc-links.js for validating internal links and anchors
- Generate llms.txt and llms-full.txt for LLM-friendly documentation
- Create downloadable source bundles (bmad-sources.zip, bmad-prompts.zip)
- Suppress MODULE_TYPELESS_PACKAGE_JSON warning in Astro build
- Output directly to build/site for cleaner deployment
Website architecture:
- Add rehype-markdown-links.js plugin to transform .md links to routes
- Add site-url.js helper for GitHub Pages URL resolution with strict
validation (throws on invalid GITHUB_REPOSITORY format)
- Custom Astro components: Banner, Header, MobileMenuFooter
- Symlink docs/ into website/src/content/docs for Starlight
Documentation cleanup:
- Remove Docusaurus _category_.json files (Starlight uses frontmatter)
- Convert all docs to use YAML frontmatter with title field
- Move downloads.md from website/src/pages to docs/
- Consolidate style guide and workflow diagram docs
- Add 404.md and tutorials/index.md
---------
Co-authored-by: forcetrainer <bryan@inagaki.us>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add documentation website with Docusaurus build pipeline
* feat(docs): add AI discovery meta tags for llms.txt files
- Add global headTags with ai-terms, llms, llms-full meta tags
- Update landing page link to clarify AI context purpose
* fix(docs): restore accidentally deleted faq.md and glossary.md
Files were removed in 12dd97fe during path restructuring.
* fix(docs): update broken project-readme links to GitHub URL
* feat(schema): add compound trigger format validation
- Module discovery now scans entire project recursively for install-config.yaml
- Removed hardcoded module locations (bmad-custom-src, etc.)
- Modules can exist anywhere with _module-installer/install-config.yaml
- All modules treated equally regardless of location
- No special UI handling for 'custom' modules
- Core module excluded from selection list (always installed first)
- Only install-config.yaml is valid (removed support for legacy config.yaml)
Modules are now discovered by structure, not location.
- Implement KiroCliSetup class extending BaseIdeSetup
- Generate 21 agents from YAML sources with JSON configs and markdown prompts
- Add runtime resource loading and numbered menu formatting
- Include BMad Core validation for required agent fields
- Fix agent naming conventions to prevent double prefixes
- Add .kiro/ directory to gitignore
Follows BMad Method standards for IDE installer integration.
Co-authored-by: Brian <bmadcode@gmail.com>
Major Changes:
- Add sample custom agents demonstrating installable agent system
- commit-poet: Generates semantic commit messages (BMAD Method repo sample)
- toolsmith: Development tooling expert with knowledge base covering bundlers, deployment, docs, installers, modules, and tests (BMAD Method repo sample)
- Both agents demonstrate custom agent architecture and are installable to projects via BMAD installer system
- Include comprehensive installation guides and sidecar knowledge bases
- Add bmad-quick-flow methodology for rapid development
- create-tech-spec: Direct technical specification workflow
- quick-dev: Flexible execution workflow supporting both tech-spec-driven and direct instruction development
- quick-flow-solo-dev (Barry): 1 man show agent specialized in bmad-quick-flow methodology
- Comprehensive documentation for quick-flow approach and solo development
- Remove deprecated tech-spec workflow track
- Delete entire tech-spec workflow directory and templates
- Remove quick-spec-flow.md documentation (replaced by quick-flow docs)
- Clean up unused epic and story templates
- Fix custom agent installation across IDE installers
- Repair antigravity and multiple IDE installers to properly support custom agents
- Enable custom agent installation via quick installer, agent installer, regular installer, and special agent installer
- All installation methods now accessible via npx with full documentation
Infrastructure:
- Update BMM module configurations and team setups
- Modify workflow status paths to support quick-flow integration
- Reorganize documentation with new agent and workflow guides
- Add custom/ directory for user customizations
- Update platform codes and installer configurations
Antigravity respects .gitignore rules which blocks access to workflow files
in .agent/workflows/, preventing custom workflows from being discovered.
Removing .agent from gitignore to allow Antigravity to scan workflow files.
Note: Codex and Claude Code ignore .gitignore when scanning for custom
prompts, so this only affects Antigravity users.
* feat: Add Google Antigravity IDE installer
Implements installer for Google Antigravity IDE with flattened slash command
naming to match Antigravity's namespace requirements.
Key features:
- Flattened file naming (bmad-module-agents-name.md) for proper slash commands
- Subagent installation support (project-level or user-level)
- Module-specific injection configuration
- Agent, workflow, task, and tool command generation
Implementation:
- Added AntigravitySetup class extending BaseIdeSetup
- Extracted flattenFilename() to BaseIdeSetup for reuse across IDE handlers
- Uses .agent/workflows directory structure
- Supports both interactive and non-interactive configuration
Fixes:
- Proper namespace isolation: /bmad-module-agents-dev instead of /dev
- Prevents conflicts between modules with same agent names
Note: This installer shares 95% of its code with claude-code.js.
Future refactoring could extract common patterns to IdeWithSlashCommandsSetup
base class (see design documents for details).
* chore: update gitignore for antigravity installer
---------
Co-authored-by: Brian <bmadcode@gmail.com>
Alex Verkhovsky