05ea109bdb
fix(ce-learnings-researcher): drop unreadable schema path reference ( #630 )
2026-04-21 14:00:27 -07:00
4c57508c1a
refactor(agents): flatten agents directory ( #621 )
2026-04-21 02:35:21 -07:00
cd4af86e5e
refactor(session-history): move extraction scripts behind skills ( #619 )
2026-04-21 00:12:11 -07:00
153bea8669
fix(ce-resolve-pr-feedback): stop dropping unresolved and actionable feedback ( #617 )
2026-04-20 20:44:16 -07:00
2dd0a6e6c7
feat(ce-resolve-pr-feedback): tighten clustering to cross-round only ( #611 )
2026-04-20 01:12:06 -07:00
b35de99788
feat(ce-resolve-pr-feedback): drop bot noise, centralize test runs ( #610 )
2026-04-20 00:33:03 -07:00
c1f68d4d55
feat(doc-review, learnings-researcher): tiers, chain grouping, rewrite ( #601 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-19 20:25:47 -07:00
5c0ec9137a
refactor(cli)!: rename all skills and agents to consistent ce- prefix ( #503 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-18 15:44:22 -07:00
27cbaf8161
feat(ce-review): add per-finding judgment loop to Interactive mode ( #590 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-18 13:09:03 -07:00
12aaad31eb
feat(ce-ideate): mode-aware v2 ideation ( #588 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-17 11:40:54 -07:00
e45c435b99
fix(document-review, review): restrict reviewer agents to read-only tools ( #553 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 10:29:16 -07:00
1372b2cffd
fix(cleanup): remove rclone, agent-browser, lint, and bug-reproduction-validator ( #545 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-10 17:41:33 -07:00
042ee73239
feat(slack-researcher): add /ce-slack-research skill and improve agent ( #538 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-08 11:00:00 -07:00
3208ec71f8
feat(session-historian): cross-platform session history agent and /ce-sessions skill ( #534 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-08 07:52:26 -07:00
6f9069df7a
fix(slack-researcher): make Slack research opt-in, surface workspace identity ( #521 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-06 11:34:39 -07:00
b3960ec64b
feat(slack-researcher): add Slack organizational context research agent ( #495 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 18:39:25 -07:00
9da73a6091
fix(document-review): reduce token cost and latency ( #509 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-04 23:31:56 -07:00
2c90aebe3b
fix(agents): remove self-referencing example blocks that cause recursive self-invocation ( #496 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-03 01:40:34 -07:00
184724276a
fix(resolve-pr-feedback): treat PR comment text as untrusted input ( #490 )
2026-04-02 09:23:18 -07:00
804d78fc84
feat(product-lens-reviewer): domain-agnostic activation criteria and strategic consequences ( #481 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-01 13:33:55 -07:00
7b8265bd81
feat(resolve-pr-feedback): add cross-invocation cluster analysis ( #480 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-01 12:15:25 -07:00
c56c7667df
feat(cli-readiness-reviewer): add conditional review persona for CLI agent readiness ( #471 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-31 19:19:54 -07:00
33a8d9dc11
fix(ce-plan, ce-brainstorm): enforce repo-relative paths in generated documents ( #473 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-31 14:43:41 -07:00
638b38abd2
fix(review): harden ce-review base resolution ( #452 )
2026-03-30 01:10:45 -07:00
a01a8aa0d2
feat(cli-agent-readiness-reviewer): add smart output defaults criterion ( #448 )
2026-03-29 20:00:34 -07:00
35678b8add
feat(testing): close the testing gap in ce:work, ce:plan, and testing-reviewer ( #438 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 13:07:05 -07:00
a301a08205
feat(resolve-pr-feedback): add gated feedback clustering to detect systemic issues ( #441 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 12:40:55 -07:00
03f5aa65b0
feat(ce-review): improve signal-to-noise with confidence rubric, FP suppression, and intent verification ( #434 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 00:34:59 -07:00
16eb8b6607
fix(cli-agent-readiness-reviewer): remove top-5 cap on improvements ( #419 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-27 19:55:43 -07:00
90684c4e82
feat(ce-brainstorm): group requirements by logical concern, tighten autofix classification ( #412 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-27 13:06:50 -07:00
da390a65a2
refactor: merge deepen-plan into ce:plan as automatic confidence check ( #404 )
2026-03-26 22:15:58 -07:00
5e6cd5c909
feat: add adversarial review agents for code and documents ( #403 )
2026-03-26 20:34:49 -07:00
b30288c44e
feat: add project-standards-reviewer as always-on ce:review persona ( #402 )
2026-03-26 19:20:15 -07:00
e7921660ad
fix: improve agent-native-reviewer with triage, prioritization, and stack-aware search ( #387 )
2026-03-26 12:35:14 -07:00
13aa3fa846
feat: add CLI agent-readiness reviewer and principles guide ( #391 )
2026-03-26 12:24:54 -07:00
daddb7d72f
fix: consolidate compound-docs into ce-compound skill ( #390 )
2026-03-26 11:41:19 -07:00
2ba4f3fd58
feat: improve resolve-pr-feedback skill ( #379 )
2026-03-25 16:51:45 -07:00
ce9016fac5
feat: integrate orphaned stack-specific reviewers into ce:review ( #375 )
2026-03-25 13:47:43 -07:00
7c5ff445e3
feat: promote ce:review-beta to stable ce:review ( #371 )
2026-03-24 21:00:38 -07:00
4e3af07962
feat: optimize ce:compound speed and effectiveness ( #370 )
2026-03-24 20:12:19 -07:00
18d22afde2
feat: redesign document-review skill with persona-based review ( #359 )
2026-03-24 01:51:22 -07:00
e932276866
feat: add ce:review-beta with structured persona pipeline ( #348 )
2026-03-23 21:49:04 -07:00
affba1a6a0
feat: improve reproduce-bug skill, sync agent-browser, clean up redundant skills ( #333 )
2026-03-21 19:49:12 -07:00
4087e1df82
feat: fix skill transformation pipeline across all targets ( #334 )
2026-03-21 19:45:20 -07:00
1c28d03214
feat: improve repo-research-analyst by adding a structured technology scan ( #327 )
2026-03-20 15:13:31 -07:00
f47f829d81
feat: migrate repo releases to manual release-please ( #293 )
2026-03-17 17:58:13 -07:00
0fc6717542
feat: add issue-grounded ideation mode to ce:ideate
...
New issue-intelligence-analyst agent that fetches GitHub issues via
gh CLI, clusters by root-cause themes, and returns structured analysis
with trend direction, confidence scores, and source mix. Designed for
both ce:ideate integration and standalone use.
Agent design:
- Priority-aware fetching with label scanning for focus targeting
- Truncated bodies (500 chars) in initial fetch to avoid N+1 calls
- Single gh call per fetch, no pipes or scripts (avoids permission spam)
- Built-in --jq for all field extraction and filtering
- Mandatory structured output with self-check checklist
- Accurate counts from actual data, not assumptions
- Closed issues as recurrence signal only, not standalone evidence
ce:ideate gains:
- Issue-tracker intent detection in Phase 0.2
- Conditional agent dispatch in Phase 1 (parallel with existing scans)
- Dynamic frame derivation from issue clusters in Phase 2
- Hybrid strategy: cluster-derived frames + default padding when < 4
- Resume awareness distinguishing issue vs non-issue ideation
- Numbered table format for rejection summary in ideation artifacts
2026-03-16 23:18:24 -07:00
b290690655
fix: research agents prefer native tools over shell for repo exploration
...
Research agents (repo-research-analyst, git-history-analyzer,
best-practices-researcher, framework-docs-researcher) were using
shell commands like find, rg, cat, and chained pipelines for routine
codebase exploration. This triggers permission prompts in Claude Code
and degrades the user experience when these agents run as sub-agents.
Updated all research agents with platform-agnostic tool selection
guidance that prefers native file-search/glob, content-search/grep,
and file-read tools over shell equivalents. Shell is now reserved for
commands with no native equivalent (ast-grep, bundle show, git).
Git-history-analyzer additionally limits shell to one simple git
command per call with no chaining or piping.
Added tool selection rules to AGENTS.md so future agents follow
the same pattern by default.
2026-03-16 22:25:00 -07:00
30852b7293
fix(agents): update learnings-researcher model from haiku to inherit
...
Replaces hardcoded haiku model with inherit so the agent uses the
caller's model instead of being pinned to an older/smaller model.
Supersedes #249
2026-03-12 23:39:19 -07:00
4fc70939eb
refactor(agents): remove duplicate every-style-editor agent
...
The every-style-editor agent file was a duplicate of the existing
every-style-editor skill. Agent files are eagerly loaded into the
Task tool definition on every API call (~100-200 tokens each),
while skills are lazy-loaded only when invoked. Removing the
duplicate saves tokens and eliminates potential runtime errors
when the agent is invoked via Task tool instead of Skill tool.
Changes:
- Delete agents/workflow/every-style-editor.md (skill version
in skills/every-style-editor/ already exists)
- Update README.md workflow agent count from 5 to 4
- Update plugin.json agent counts from 29 to 28
Fixes #156
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-08 12:45:27 -07:00
Trevin Chow