## What
Gut **context poison** — agent-facing docs that route a working agent at
DEAD mechanisms. This poisoned a live fleet-operating session (the bo
driver building the go-dark supervisor) into proposing `ao rpi` as a
continuity-loop worker. Found via a 5-way parallel poison fan-out.
**Scope: operational-surgical** (Bo's explicit call). Gut the
agent-facing *operational* guidance + *factual* errors; **LEAVE** the
README/`docs/3.0.md` product narrative (Gas-City-as-reference-substrate
is coherent, ADR-backed product design — a different altitude from Bo's
live fleet).
## Changes (10 files, surgical)
**Tier A — operational guidance (the poison that bit me):**
- `CLAUDE.md` Session Constraints: "route multi-phase work through `ao
rpi`" → the live substrate (NTM + MCP Agent Mail + `continuity-loop`);
`gc` reframed as optional-out-of-session, **not** the live substrate.
Kept the accurate "bridge REMOVED" + "load-bearing legacy" lines.
- `AGENTS.md`: dropped the deleted "scheduling daemon" (ADR-0009).
- `AGENTS-RUNTIME.md`: `ao rpi serve --help` → the real `ao` command
surface.
**Tier B — hookless-factual** (3.0 installs no hooks by default):
hookless banners on `ARCHITECTURE.md` + `reference.md` (surgical vs.
rewriting diagram internals); corrected SessionStart-hook prose in
`context-packet.md` + `vs-claude-flow.md`.
**Tier C — retired `/dream` shown as live:** marked retired in
`evolve`/`harvest`/`using-agentops` (compounding moved to Gas City).
`curate` **intentionally left** — its `--mode=dream` is the forward
replacement, not poison.
## Guardrails
- Does **not** claim `ao rpi` was deleted — the command still compiles
(`loop`/`phased`/`serve` exist); only its role as the *live workflow* is
corrected.
- registry.json unaffected (skill **bodies** only; `generate-registry.sh
--check` = OK).
## Evidence
`bash scripts/generate-registry.sh --check` → OK. Diff is 20 insertions
/ 16 deletions across 10 files.
Bounded-context: BC1-Corpus (agent-facing context docs)
Evidence: this PR diff + the parallel fan-out inventory
Closes: ag-sjz8
🤖 Generated with [Claude Code](https://claude.com/claude-code)
## What
Two bounded doctrine-reconciliation slices (one coherent arc):
**ag-88y5** — the out-of-session dispatch unit is the `/rpi`·`/evolve`
**skill**, not the `ao rpi`/`ao evolve` CLI. Per the 3.0
skills-are-the-runtime thesis (using-ntm #693 already frames it this
way), re-narrate the **live** doctrine surfaces so the substrate spawns
an agent that *runs the /rpi skill* over a bead:
- docs/3.0.md, docs/architecture/canonical-loop-model.md,
docs/runbooks/nightly-evolution.md
- skills/using-agentops, skills/agent-native,
skills/domain/references/factory.md
Historical surfaces (MIGRATION-3.0, ADR-0009, release notes) +
CLI-reference left as-is; the actual `ao rpi`/`ao evolve` CLI removal is
the **ag-iowf** epic (live automation callers — overnight-evolve,
release-smoke — must migrate first).
**ag-ogp5** — drop the 4 docs still asserting Gas City as THE reference
substrate → NTM+MCP+managed-agents:
- docs/ARCHITECTURE.md, docs/SCHEMAS.md,
docs/contracts/agents-write-surfaces.md,
docs/patterns/completion-notifications.md (Pattern C)
The ~37 historical/illustrative GC refs are intentionally retained (per
ag-ogp5 scope).
## Verification
regen-all --check, embedded-sync, heal --strict, registry-drift,
codex-rpi-contract, codex-artifacts --scope head — all green.
Closes-scenario: ag-88y5#docs-skills-dispatch-reframe
Bounded-context: BC4-Factory
Evidence: docs/3.0.md
## What
Adds an **AgentOps-owned, shippable `using-ntm` skill** — the missing
NTM leg of the `NTM + MCP + managed-agents` substrate doctrine
(**ag-zaoj**). Until now `automation-shape-routing` pointed **by name**
at the *proprietary* `ntm`/`vibing-with-ntm` skills, which AgentOps
can't ship — a dangling pointer for standalone users. This is original
content modeled on (not copied from) those.
## The seam: skills are the runtime, not the CLI
The skill teaches driving the open `ntm` CLI as the out-of-session
substrate: **NTM spawns Claude/Codex panes that run the `/rpi` and
`/evolve` *skills*** over a bead queue. It explicitly does **not** use
`ao rpi`/`ao evolve` CLI subprocesses — those terminal wrappers are
retired; the substrate dispatches the whole loop as one invocable skill.
## What lands (15 files, +~440)
- `skills/using-ntm/SKILL.md` + `skills-codex/using-ntm/SKILL.md` (twin)
— the new skill.
- `automation-shape-routing` (+ codex twin) — dangling
`ntm`/`vibing-with-ntm` pointers now route to the owned `/using-ntm`;
`ntm` stays as the CLI tool.
- Six derived surfaces regenerated: `registry.json`, skill-domain-map,
SKU catalog, codex hashes/manifest, context-map; + skill-disposition row
and skill-count bumps (80 → 81) in PRODUCT / ARCHITECTURE / SKILLS /
domain-map / BDD-Gherkin.
## E2E verification (against the real `ntm` CLI)
Per the directive (no `ao rpi`/`ao evolve`): verified every `ntm`
subcommand the skill cites exists
(`spawn/send/activity/attach/doctor/deps/kill/health`) and **fixed the
documented flag to the real `--pane=N` syntax** (it had `--pane N`).
`ntm doctor` runs (bv ✓ / bd ✓ / am ⚠). `docs/cli-surface.*` drift
excluded (pre-existing, unrelated).
## Follow-up (not in this PR)
`ao rpi`/`ao evolve` CLI are slated for retirement; `docs/3.0.md` + the
recent Gas City-prune PRs still reference `ao rpi <bead>` as the
dispatch unit and need a skills-not-CLI reconciliation pass.
## Verification
- `regen-all.sh --check` ALL GREEN · registry-drift PASS · codex parity
PASS · skill-isolation/size PASS · markdownlint 0.
Closes-scenario: ag-zaoj#using-ntm-skill
Bounded-context: BC4-Factory
Evidence: skills/using-ntm/SKILL.md
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
## Phase 2 — migrate salvaged memory onto bd (epic `ag-5u50`)
**Stacked on #691 (Phase 1).** Review/merge that first; this PR's diff
is Phase-2-only.
Second arc of the **bd-first-memory-migration** skill: take the Gate-A
keepers and stand up bd as the single source of truth — typed memories
with provenance, decay-ranked recall, a generated MEMORY.md cache, and
one unified write path.
### What's in it (beads ag-5u50.10–.14)
- **`.11` `mem.py`** — typed wrapper over bd keys (fenced `<!--mem-->`
header), injectable `BdStore`/`FakeStore` adapter, `parse`/`render` +
**decay-rank** per DATA-MODEL.
- **`.12` `recall.py`** — decay-ranked, token-budgeted recall; bumps
`access_count` (the read signal feeding utility/promotion).
- **`.14` `gen_memory_md.py`** — regenerate the thin, read-only
MEMORY.md cache from bd (permanently fixes the bloat mode).
- **`.13` `remember.py`** — unified write entrypoint (all harnesses →
bd).
- **`.10` `import_memories.py`** — idempotent salvage import with
provenance + import-ledger, **write-paced** (bd auto-commit OOM guard),
`--dry-run`.
### Verification
- **11 hermetic L2 tests** (`tests/test_phase2_migrate.py`), no
`bd`/`ao` dependency — round-trip, decay ordering, supersede exclusion,
episodic-vs-feedback decay, access bump, idempotent import, dry-run,
write-path provenance — all green (17 total with Phase 1).
- **7 Gherkin scenarios** (`references/migrate.feature`).
- Scripts 100-col clean; codex twin hashes refreshed; full local gate
sweep green (skill-lint, codex artifacts/coverage, registry,
context-map, counts, three-gap).
> **CI note:** opened on **local-green** — GitHub Actions stopped
dispatching workflow runs repo-wide ~20:20 (a GitHub-side outage/quota
issue, not this code). All gates verified locally; cloud CI will run
once dispatch recovers.
### Scope guardrails
Writes to bd only — no Phase-3 GC/retire here (that's gated behind the
rollback test). The destructive dogfood on the live box stays
human-gated (Gate C).
Closes-scenario: ag-5u50#phase2-migrate
Bounded-context: BC1-Corpus
Evidence: skills/bd-first-memory-migration/tests/test_phase2_migrate.py
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
## What
Round-2 Gas City doctrine sweep (**ag-94vu**). Re-narrates the **5 named
skill surfaces** that still framed Gas City as THE live reference
substrate (present-tense operator instructions) to the canonical
substrate trio — **NTM (tmux swarm) + MCP (`ao mcp serve`) +
managed-agents (`ao agent`)** — matching [`docs/3.0.md`](docs/3.0.md).
Driver: post-mortem checkpoint #6 Judge-3 FAIL ("the repo does not yet
speak one doctrine").
## Surfaces (9 insertions / 9 deletions, 5 files)
- `skills/domain/references/factory.md` — "Gas City is the reference
substrate" → the NTM/MCP/managed-agents trio; "Mayor-driven / `gc
sling`" → **swarm-driven** dispatch.
- `skills/scope/SKILL.md` — cron-cadence orchestration reference.
- `skills/session-bootstrap/SKILL.md` — substrate submit reference.
- `skills/SKILL-TIERS.md` — dream retired-pointer note.
- `skills-codex/using-agentops/SKILL.md` — **codex-twin parity**:
dropped the stale `gc` runtime-mode row for the canonical `substrate`
row (the Claude twin was already correct; this one slipped in #679).
## Bounded by design
This PR is the coherent **"live skill operator-instructions speak one
doctrine"** slice. A repo-wide grep shows ~35 more refs across other
skills + `docs/` narrative; bundling them would reproduce the #682
mega-PR that was rejected for sprawl. Deferred to tracked follow-ups:
- **ag-r6g1** — round-3 narrative sweep (remaining skills/ + docs/ ~35
refs; many docs already frame GC correctly as "the reference" — triage
required).
- **ag-82pv** — remove orphaned
`GasCityPhaseEvidence*`/`GasCityTranscript*` dead types in
`cli/internal/rpi/artifacts.go`.
## Verification (local, green)
- codex-parity-drift: PASS · registry-drift: PASS (80) ·
skill-catalog-drift: up-to-date · skill-isolation: PASS · skill-size:
0/0 · markdownlint: 0 errors.
- Residual live-substrate grep over the 5 surfaces: clean.
Closes-scenario: ag-94vu#live-substrate-renarration
Bounded-context: BC1-Corpus
Evidence: skills/domain/references/factory.md
## What
Operator-authorized (Bo, 2026-06-02). Strips the remaining **Gas City**
(`gastown`) coupling from AgentOps and reconciles the **split-doctrine
state** on `main` that the #672–#676 post-mortem flagged: canonical docs
(#676) said NTM+MCP+managed-agents while user-facing docs still
described Gas City as the reference substrate.
The out-of-session substrate is now uniformly **NTM** (local tmux swarm)
+ **MCP** (`ao mcp serve`, shipped) + **managed-agents** (`ao agent`).
AgentOps adopts a substrate; it owns none. Closes **ag-124p** (and
resolves **ag-h93p** — the claude.json gc-hook decouple).
## Deleted (load-bearing surfaces, per the bead's verified scope)
- `packs/agentops/` (the reference City) + root `city.toml`
- `skills/using-gc` + `skills-codex/using-gc` (+
`tests/scripts/using-gc-skill.bats`)
- `gc prime/nudge/mail/hook` wiring in `cli/hooks/claude.json` → now
hookless, matching 3.0 doctrine
## Doc sweep (the split-doctrine fix the post-mortem required)
- **README.md, docs/MIGRATION-3.0.md, docs/dependencies.md,
docs/activation-profiles.md** re-narrated to the substrate trio (the
four files the verdict named)
- AGENTS.md / CLAUDE.md substrate bullets; `dream` skill (+codex twin)
retirement pointer; `shared` / `agent-native` / `using-agentops`
cross-refs; skill-dispositions, context-map, sku-catalog, google-sre
convergence map
## Regenerated derived surfaces
Skill counts (81→80), `registry.json`, `skills/catalog.json`,
context-map, skill-domain-map, codex hashes (14) + manifest, SKILL-TIERS
— all via the generators, validated drift-free.
## Scope boundaries / follow-ups
- **`cli/internal/doctor/fix_bridges.go`** still carries a gc-bridge
detector/fixer subsystem. Out of the bead's verified scope; degrades
gracefully (stat-checks, returns empty when `gc`/`city.toml` absent);
removing it is a test-backed Go change → **follow-up bead**.
- **CLAUDE.md "Gas City bridge — REMOVED"** note kept intentionally:
it's an anti-re-coupling record, not substrate-framing.
- The local-only **bd-closeout** pre-push check (not in CI) is a
pre-existing gap on `main` (its AGENTS.md has no `bd dolt push` line) —
untouched here.
- `thesis-stability` gate FAIL, if present, is the pre-existing
README/PRODUCT/GOALS tagline drift, unrelated to this PR (my
README/PRODUCT edits are the dependency table + skill-count numbers, not
the tagline).
## Verification
`go build ./...` + `go vet` green · skill schema (80/80) + integrity
(heal --strict clean) + lint suite (0 fail) + codex parity green ·
sku-catalog & context-map drift gates green · zero broken markdown links
to deleted paths.
Closes-scenario: ag-124p#gc-coupling-strip
Bounded-context: BC5-Runtime
Evidence: docs/MIGRATION-3.0.md
## What
First child of **ag-7s9fo** (Make Managed/SDK agents AgentOps-native).
Adds the **/agent-native** dual-runtime skill documenting the **hookless
reframe** of the retired "port the ~50 hooks" idea.
An out-of-session Claude (Managed Agent / Agent SDK loop / self-hosted
sandbox) becomes AgentOps-native via three things — **never hooks**:
1. **Bundle AgentOps skills** into the Agent definition (same `skills/`
files, no fork).
2. **Expose the `ao` CLI as a callable tool** (MCP/shell-tool) so the
loop self-bootstraps + self-validates.
3. **Gate outputs through the SAME CI** as interactive work.
Extends `standards` + `converter`. The SDK hooks become an *optional
thin adapter*, never the enforcement boundary. Managed Agents are NOT
ZDR → no holdout/PII in the agent definition.
## How
Built through the hardened scaffold (ag-cw2y → ag-ekyq → ag-j4l1) — all
6 derived surfaces regenerated in one shot (registry, domain-map,
context-map, counts, codex twin+manifest+marker, dispositions
BC5-Runtime, SKILL-TIERS, using-agentops catalog, embedded sync).
Reverted the swept-in pre-existing drift (6 codex hashes + cli-surface)
per the changed-files-scoped triage.
Caught + fixed an `INVALID_AO_CMD` heal finding: `ao standards` isn't a
command — `standards` is a loaded checklist enforced via `ao validate` +
CI (corrected the references).
## Scope note
The skill documents the *intended* `ao agent bundle` / `ao mcp serve` /
`agent-output-validate.yml` surfaces — those are the sibling child beads
(ag-jspr, ag-higd, ag-mptr). This PR is the skill-doc slice only.
## Evidence
- `heal.sh --strict skills/agent-native` → clean
- `audit-codex-parity.sh --skill agent-native` → pass
- `validate-codex-generated-artifacts.sh --scope worktree` → pass
- `generate-{registry,skill-domain-map}.sh --check` → clean;
`check-registry-drift.sh` → no drift
Closes-scenario: ag-2wln#agent-native
Bounded-context: BC5-Runtime
Evidence: skills/agent-native/SKILL.md
## What
Adds the **/eval-outcomes** dual-runtime skill — the user-facing
documentation wrapper for the already-merged `ao eval outcomes
compile/ingest` capability (the Outcomes epic ag-hdqu0, capability beads
.1/.2/.4/.5/.6/.7/.9 all merged). This is the final ag-hdqu0 child.
eval-outcomes documents Outcomes as a **grading transport** that EXTENDS
`validation` + `ratchet` — a *projection* of the locked eval substrate
(`SCHEMA.md`), never an alternate bar. Holdout `target`/`ground_truth`
never leaves the boundary (Managed Agents are not ZDR).
## How
Built through the ag-cw2y scaffold + the 6-surface new-skill discipline
in one shot:
- `skills/eval-outcomes/SKILL.md` + `skills-codex/eval-outcomes/`
(parity_only twin + prompt.md)
- override catalog + manifest/marker (`register-new-codex-skill.sh`)
- dispositions row (BC2 Validation) + SKILL-TIERS row + using-agentops
catalog
- registry.json SKU catalog + domain-map + context-map + narrative
counts + embedded sync
Reverted pre-existing-main drift swept in by generators (6 unrelated
codex artifact hashes, cli-surface.*) per the changed-files-scoped
triage.
## Evidence
- `audit-codex-parity.sh --skill eval-outcomes` → pass
- `heal.sh --strict skills/eval-outcomes` → clean
- `validate-codex-override-coverage.sh` → 80 skills pass
- `validate-codex-generated-artifacts.sh --scope worktree` → pass
- `generate-{registry,skill-domain-map,context-map}.sh --check` → clean;
`check-registry-drift.sh` → no drift
(Local fast pre-push gate references a missing
`scripts/audit-codex-hooks.sh` — pre-existing gate-infra drift absent on
main, not this PR; CI is the authoritative gate.)
Closes-scenario: ag-hdqu0.8#eval-outcomes-skill
Bounded-context: BC2-Validation
Evidence: skills/eval-outcomes/SKILL.md
## What
Adds a `operating-loop-workflow` skill that delivers the
`operating-loop` Workflow-tool script to **installed plugin users** and
invokes it.
## Why
Claude Code plugins do **not** load `.claude/workflows/*.js` (recognized
components are `skills/`, `commands/`, `agents/`, `hooks/`, …). PR #594
force-added the script so it *ships in the plugin cache*, but an
installed user still wouldn't see `/operating-loop`. This skill is the
delivery vehicle.
## How
On `/operating-loop-workflow`, the skill:
1. Idempotently copies
`${CLAUDE_PLUGIN_ROOT}/.claude/workflows/operating-loop.js` →
`~/.claude/workflows/operating-loop.js` (copy-if-newer; never clobbers
user edits).
2. Invokes `Workflow({name:'operating-loop', args})` (supports
`{mode:'plan'}` for the plan-only half).
Named `operating-loop-workflow` (not `operating-loop`) to avoid
colliding with the workflow's own auto-surfaced `/operating-loop` in the
dev repo.
## Registries updated
- `skills/SKILL-TIERS.md` row + `sync-skill-counts.sh` (→ 76 total, 66
user-facing)
- `docs/contracts/skill-dispositions.yaml` + regenerated
`docs/reference/agentops-skill-domain-map.md` (76/76)
- `docs/contracts/context-map.md`,
`docs/reference/agentops-domain-evolution-bdd.md` count
## Validation
- `scripts/pre-push-gate.sh --fast` passed (registry-drift,
skill-domain-map golden gate, domain-evolution plan all green)
- `generate-skill-domain-map.sh`: 76 skills, 76 dispositions, clean
Closes-scenario: agentops-7m7a#plugin-deliver-operating-loop
Bounded-context: BC3-Loop
Evidence: docs/reference/agentops-skill-domain-map.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
## What
Builds the GC on-ramp for AgentOps 3.0: a `using-gc` skill that guides
agents on the `gc` (Gas City) CLI exactly like the `bd` protocol guides
them, plus a complete, accurate tool-dependency declaration. **Additive
— no existing behavior changed.**
THE MODEL (operator): "use gc like we use bd" — skills GUIDE agents on
the gc workflow; `ao` does NOT wrap gc. gc is a guided out-of-session
dependency, same as bd.
## Changes
1. **New skill `skills/using-gc/`** — agent-facing guide to running
AgentOps on Gas City, mirroring the bd-protocol style. Covers the gc
primitives (City/`city.toml`, Rig, Pack, Agent, Order, Formula, mayor +
refinery), the end-to-end workflow (`gc start` → `gc rig add` → the
mayor-driven dispatch loop: `bd ready` → `gc sling <rig>/refinery
<bead>` → worker runs `ao rpi <bead>`), cron `exec` Orders for
maintenance (`ao compile`/`ao maturity`), and is HONEST about the
order-auto-dispatch gap (no per-fire var-binding → dispatch is
mayor-driven today; order-auto-dispatch is an upstream-GC item,
soc-5jwah). References the real pack at `packs/agentops/` and
`docs/3.0.md`. Two reference docs + a `.feature` (linked +
`@covered-by:` a new bats test).
2. **Complete dependency declaration** — derived from `ao doctor` tool
checks (`ao`, `awk`, `bash`, `bd`, `cass`, `gc`, `git`, `tmux`) +
`scripts/install*.sh` + the shared fallback table. Classified REQUIRED
(ao, git, runtime), TRACKING (bd + Dolt), ORCHESTRATION (gc,
out-of-session), PR/CI (gh), BUILD-FROM-SOURCE (go), UTILITIES (jq, rg,
curl, openssl, sha256sum, tmux, cass). Landed in: `docs/dependencies.md`
(canonical detail, catalogued in documentation-index), a README
"Requirements" section (summary), and the expanded
`skills/shared/SKILL.md` fallback table (now includes gc, gh, go, jq,
rg).
3. **Fixed stale `using-agentops/SKILL.md:212`** — the runtime-mode `gc`
row described the DELETED `runtime=gc` auto-executor ("ao rpi
auto-selects gc executor", "gc event bus"). Reframed to the mayor-driven
reference City: gc dispatches whole `ao rpi`/`ao evolve` loops; there is
no in-CLI `runtime=gc` mode.
4. **Brief gc pointer** in repo `CLAUDE.md` + `AGENTS.md` near the bd
section, pointing to the using-gc skill (no skill content duplicated).
## Gates (all green locally)
- `sync-skill-counts.sh`: 80→81 total, 9→10 internal — PASS, verified
consistent.
- `validate-context-map-drift`: regenerated
docs/contracts/context-map.md — matches.
- Codex twin `skills-codex/using-gc/` created (`$skill` notation, no
Claude primitives); registered across the 4 catalog surfaces;
`regen-codex-hashes.sh` clean; `audit-codex-parity` PASS; 81 codex
artifacts.
- `generate-registry.sh` (81 skills) — up to date.
- skill-domain-map disposition added (BC5 Runtime) + regenerated golden
— matches; registry-drift narrative counts fixed (80→81).
- plugin-load-test (no symlinks — references copied), skill-schema
(81/81), skill-frontmatter (81/81), skill-dependency-check, heal.sh
--strict (clean), scenario-test-linkage (PASS, new .feature linked via
bats), markdownlint (0 errors), doc-release-gate (PASS).
- New bats test `tests/scripts/using-gc-skill.bats` (5/5).
- Codex description aggregate budget bumped 2700→2800 (catalog grew to
81; same precedent as the 2600→2700 bump when expert-council landed).
- `cd cli && go build && go vet && go test ./cmd/ao/` green (embedded
using-agentops copy synced via `make sync-hooks`).
Closes-scenario: ag-p4p#gc-onramp
Bounded-context: BC5-Runtime
Evidence: skills/using-gc/SKILL.md
* docs(readme): lead with problem/solution and the executable-spec chain
* feat(skills): add expert-council — adversarial persona council
Named domain-expert personas duel via the dueling-idea-wizards route (verdict -> 0-1000 cross-scoring -> reveal -> score matrix). judgment tier. Slated for absorption into council --mode=debate per soc-ml4l.
* docs(council): add council-modes.feature acceptance spec for soc-ml4l
* refactor(council): formalize brainstorm/debate/verdict mode taxonomy
Refactor `council` into the three-mode taxonomy settled by the 2026-05-17
cross-vendor taxonomy duel (soc-ml4l). `--mode` selects one of exactly three
deliberation patterns — brainstorm (diverge), debate (contend), verdict
(converge); verdict is the default. `--focus`/`--depth`/`--runtime`/`--roster`
are orthogonal knobs, never modes.
- New `references/modes.md` — full taxonomy, mode-invariant lifecycle
(convene/brief/deliberate/synthesize/record), knob aliases.
- Rename the `--debate` flag (a verdict intensifier) to `--adversarial`;
the word `debate` now names the contend mode. `debate-protocol.md` ->
`adversarial-protocol.md`.
- Absorb `expert-council` as `--mode=debate`: move `dueling-route.md` into
`council/references/`; `expert-council` is now a 1-release thin alias ->
`/council --mode=debate`.
- `research` verb folds into brainstrom (`--focus=research`); `validate`
stays a verdict alias.
- Sync codex twins, SKILL-TIERS, using-agentops catalog, validate.sh
behavioral checks, codex hashes.
Acceptance: every scenario in council/references/council-modes.feature holds.
---------
Co-authored-by: Codex <codex@example.invalid>
#275's billboard refactor thinned process-skill SKILL.md files and moved
detail into references/, but the validate contracts still grepped SKILL.md.
skill-lint + smoke-test: relax content-presence checks in crank/implement/
post-mortem/swarm validate.sh to scan the skill as a unit (SKILL.md +
references/); structural/identity checks stay SKILL.md-only. test-first-smoke
updated to match relocated SPEC/TEST WAVE + Step 0/4 headings.
skill-lint line caps: trim flywheel 310 -> 286 (cap 300), using-agentops
261 -> 239 (cap 250) by removing redundant prose, no content lost.
skill-integrity: link 3 orphaned references (crank/branch-isolation,
validation/flags + release-readiness-gates).
codex parity: regenerate stale skills-codex source hashes (77 skills).
Local: run-all.sh PASS, heal.sh --strict clean, smoke-test PASS.
The codex artifact metadata gate enforces source/codex twin commits as a
matched pair. The previous commits modified skills/using-agentops and
skills/validation without touching their twins.
- skills-codex/using-agentops/SKILL.md: add $system-tuning row in the
Advanced Skills table (mirrors /system-tuning add in source)
- skills-codex/validation/SKILL.md: trim same two redundant sections as
source (Expensive Command Policy and DAG preamble code block)
- skills-codex/.agentops-manifest.json + per-skill .agentops-generated.json
hashes auto-refreshed by regen-codex-hashes.sh
Validation: codex parity PASS for both skills, heal-strict clean,
validate-codex-generated-artifacts (staged scope) PASS.
Adds a 2400-char aggregate budget for skills-codex/*/SKILL.md `description:`
fields in tests/skills/test-token-budgets.sh, then trims each skill's description
to fit (catalog now 2146/2400). Both Claude and Codex SKILL.md descriptions
are kept in sync; codex .agentops-generated.json hashes regenerated.
Adds --repair-shape to scripts/audit-codex-hooks.sh: when ~/.codex/hooks.json
is missing or in legacy-flat shape, rewrites it from hooks/codex-hooks.json
with the active plugin_root (read from .agentops-codex-install.json) and
backs up any prior file. Covered by new test_repairs_legacy_flat_shape.
Memory decay (4 .agents/ files) bumped by the SessionStart inject hook.
Fourth subcommand under ao agents. Rolls up the existing inspect (#141)
and lint (#143) outputs and adds two new cross-surface checks:
- "orphan skills" — skills/<name>/ exists but no .agents/<name>/
- "undocumented dirs" — .agents/<name>/ is neither catalogued nor a skill
Default exit policy mirrors lint: non-zero only when the lint script
fails. --strict also fails on any orphan or undocumented entry, suitable
for CI gates.
Reuses parseAgentsAllowlist + discoverActiveSkills from agents.go and
re-implements the lint exec path inline (so doctor can keep going past
a lint failure and still collect the cross-surface report). JSON output
via the AgentsDoctorReport shape.
9 tests cover registration, helper functions (sorted output, hidden-dir
skipping, missing-agents-dir tolerance), text/JSON shapes, and exit
codes (lint-failure pass-through, --strict orphan exit). COMMANDS.md
regenerated. using-agentops skills (Claude + Codex) updated to mention
the new subcommand; codex hashes regenerated; parity drift + audit
both pass.
Closes agentops-zw6.
Per the /evolve constraint that any new user-facing CLI surface needs both
Claude and Codex skill mentions, surface 'ao agents inspect' and
'ao agents lint' (added in #141 + #143) under the Knowledge Flywheel
section of both skills/using-agentops/SKILL.md and skills-codex/using-agentops/SKILL.md.
Codex hashes regenerated. check-codex-parity-drift.sh and
audit-codex-parity.sh both pass.
Closes agentops-13z.
Rename the athena skill to compile — a descriptive name that communicates
what it actually does. Extend with Karpathy's LLM Knowledge Bases architecture:
- New compile phase: LLM reads raw .agents/ artifacts and produces interlinked
markdown wiki at .agents/compiled/ with index.md, log.md, backlinks
- New lint phase: detects contradictions, orphan pages, stale claims, coverage gaps
- Pluggable compute backend via AGENTOPS_COMPILE_RUNTIME (ollama|claude|openai)
- Hash-based incremental compilation (only recompile changed sources)
- compile.sh engine with security fixes (no shell injection, path traversal guard)
- Full rename across 93 files: skills, docs, CLI, tests, hooks, scripts, codex
Existing Mine → Grow → Defrag cycle preserved as phases within the larger
compile workflow. No vector DB — compiled wiki IS the retrieval layer.
gc executor is now the default when gc binary (>= 0.13.0) and
city.toml are available. Falls back to stream executor otherwise.
Schema fixes found by L3 live controller tests:
- GCController uses running (bool), not state (string)
- gc event emit uses --payload flag, not --data
Test infrastructure: gcMock with TestHelperProcess pattern for
deterministic exec injection. 107 test cases across L1 (unit),
L2 (component chain), and L3 (live gc controller).
Skills updated to document gc as default runtime mode.
Crank failure taxonomy updated from tmux to gc session commands.
Bo