dd25db036c
fix(ce-sessions): move orchestration to skill, reshape historian to synthesis-only
...
The ce-session-historian agent deadlocked when dispatched as a subagent in
Claude Code because its first action was Skill(ce-session-inventory), and
subagents cannot invoke the Skill tool (anthropics/claude-code#38719). The
spinner hung at "Initializing…" indefinitely; after timeout the orchestrator
received a spurious "user doesn't want to proceed" rejection.
The fix removes every code path that has a subagent calling Skill:
- Move 4 extraction scripts into plugins/compound-engineering/skills/ce-sessions/scripts/
(single home; ce-session-inventory and ce-session-extract skills deleted)
- Rewrite ce-sessions/SKILL.md as the full orchestrator: discovery, branch +
keyword filtering, scan-window selection, top-5 deep-dive cap, mktemp
scratch dir, per-session extraction with new --output PATH flag (extraction
bytes write directly to scratch, never round-trip through main-context tool
results), dispatch of synthesis-only historian
- Reshape ce-session-historian.agent.md to synthesis-only: receives file
paths in dispatch prompt, reads via native file-read tool, returns prose
findings. No Skill calls, no Bash discovery, no orchestration logic
- Update ce-compound Phase 1 to delegate to ce-sessions via the platform's
skill-invocation primitive (semantic-prose form per plan-handoff.md line 57
convention, not literal Skill(...) syntax). Specifies dispatch ordering so
the parallel research subagents and ce-sessions still run concurrently —
wall-clock parallelism preserved
- Add --output PATH to extract-skeleton.py and extract-errors.py: when set,
scripts write to file and emit only a one-line JSON status to stdout.
Stdout-mode behavior preserved when omitted (additive API change)
- Add regression test (tests/skills/ce-session-historian-no-skill-tool.test.ts)
asserting the agent body never instructs Skill(ce-session-inventory),
Skill(ce-session-extract), or any literal Skill(...) tool-call expression
- Register ce-session-inventory and ce-session-extract in legacy-cleanup
lookups (STALE_SKILL_DIRS, LEGACY_ONLY_SKILL_DESCRIPTIONS, and
EXTRA_LEGACY_ARTIFACTS_BY_PLUGIN) so existing flat-installs sweep on upgrade
- Fix broken See Also links in docs/skills/ce-sessions.md
The bug is structurally gone: no subagent in the post-refactor flow ever
invokes the Skill tool. Plan with full design rationale, alternatives
considered (including issue #794 's Options 1 and 2), and implementation
units lives at docs/plans/2026-05-08-001-fix-ce-sessions-orchestration-refactor-plan.md.
All 1337 bun tests pass; bun run release:validate passes (37 skills,
49 agents). Closes #794 .
2026-05-08 09:33:48 -07:00
6fc57c501f
fix(ce-debug): right-size triage and tighten hypothesis discipline ( #796 )
2026-05-08 08:09:47 -07:00
7f5297a05f
docs(ce-ideate): sync user-facing doc with topic-surface decomposition ( #790 )
2026-05-07 02:39:30 -07:00
168fad4ac2
fix(ce-ideate): bound scope and add topic-surface decomposition ( #787 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-07 02:21:08 -07:00
d299868b8f
docs(skills): reframe README around the 4-step core loop ( #786 )
2026-05-06 09:58:43 -07:00
65c278c031
docs(skills): sync ce-doc-review and ce-plan with PR #780 ( #782 )
2026-05-05 17:20:04 -07:00
a1698b7a0e
docs(skills): add user-facing skill docs at docs/skills/ ( #773 )
2026-05-04 17:39:48 -07:00
dde9256362
feat(riffrec-feedback-analysis): add Riffrec feedback skill with three-path routing ( #747 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-04 11:12:56 -05:00
0c515c06fe
fix(ce-plan): inline post-generation menu routing so option 1 actually starts /ce-work ( #715 )
...
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com >
2026-04-28 10:33:11 -07:00
8cc07acb52
docs(solutions): refresh stale references and prune obsolete doc ( #712 )
2026-04-27 22:17:02 -07:00
41e7f72ab6
feat(ce-brainstorm,ce-plan): surface agent's scope synthesis before doc-write ( #705 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-27 20:34:30 -07:00
cd2fc67c3f
fix(commit-push-pr): branch from fresh remote base to prevent stale-base contamination ( #708 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-27 16:39:17 -07:00
ad9577e732
fix(ce-code-review): tighten autofix_class rubric for safe_auto/gated_auto boundary ( #695 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-25 21:03:43 -07:00
9ba41a14ca
fix(ce-code-review): replace LFG with best-judgment auto-resolve ( #685 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-25 18:12:09 -07:00
bc8ae1a6b5
fix(main): recover version drift, fix stale test, document learnings ( #678 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-24 15:07:49 -07:00
fdf5fe4af5
feat(ce-demo-reel): add local save as alternative to catbox upload ( #647 )
2026-04-22 11:28:44 -07:00
5a26a8fbd3
refactor(ce-code-review): anchored confidence, staged validation, and model tiering ( #641 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-21 21:04:29 -07:00
accbd2adcf
refactor(todos): remove internal file-based todo system ( #635 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-21 18:16:13 -07:00
44ce9dd127
feat(ce-plan): add U-IDs and origin trace to plan template ( #632 )
2026-04-21 16:07:28 -07:00
6caf330363
refactor(ce-doc-review): anchor-based confidence scoring ( #622 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-21 14:54:03 -07:00
3ed4a4fa0f
feat(codex): native plugin install manifests + agents-only converter ( #616 )
2026-04-20 19:44:25 -07:00
c2d60b47be
refactor(install): prefer native plugin install across targets ( #609 )
...
Co-authored-by: John Cavanaugh <cavanaug@users.noreply.github.com >
2026-04-20 18:47:07 -07:00
d8436b9a3c
fix(ce-compound): quote YAML array items starting with reserved indicators ( #613 )
...
Co-authored-by: Nathan Vale <hi@nathanvale.com >
2026-04-20 14:01:11 -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
59dbaef376
feat(ce-release-notes): add skill for browsing plugin release history ( #589 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-04-17 02:00:37 -07:00
070092d997
feat(ce-polish-beta): human-in-the-loop polish phase between /ce:review and merge ( #568 )
...
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-16 17:55:10 -05:00
8f20aa0406
feat(ce-optimize): Auto-research loop for tuning system prompts / vector clustering / evaluating different code solution / etc ( #446 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-12 20:16:09 -07:00
354dbb7582
feat(ce-setup): unified setup skill with dependency management and config bootstrapping ( #345 )
...
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-10 17:39:43 -07:00
b979143ad0
feat(ce-demo-reel): add demo reel skill with Python capture pipeline ( #541 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-09 21:29:51 -07:00
bb59547a2e
feat(ce-work): reduce token usage by extracting late-sequence references ( #540 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-09 12:48:21 -07:00
31b0686c2e
feat(ce-work-beta): add beta Codex delegation mode ( #476 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-09 00:29:12 -07:00
320a045241
feat(ce-plan,ce-brainstorm): universal planning and brainstorming for non-software tasks ( #519 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 23:53:13 -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
4fdbdc4ac3
docs(skill-design): document research agent pipeline separation and refresh stale refs ( #510 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 11:20:44 -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
9bf3b07185
fix(ce-compound): require question tool for "What's next?" prompt ( #460 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-30 16:25:26 -07:00
44e3e77dc0
feat(git-commit-push-pr): add conditional visual aids to PR descriptions ( #444 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 14:13:25 -07:00
f93d10cf60
feat(converters): centralize model field normalization across targets ( #442 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 13:08:35 -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
4c7f51f35b
feat(ce-plan): add conditional visual aids to plan documents ( #440 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 12:18:31 -07:00
1f499482bc
fix(git-commit-push-pr): quiet expected no-pr gh exit ( #439 )
2026-03-29 11:45:27 -07:00
bd02ca7df0
feat(ce-brainstorm): add conditional visual aids to requirements documents ( #437 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 11:13:19 -07:00
3706a9764b
feat(ce-review): add headless mode for programmatic callers ( #430 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-28 16:09:21 -07:00
f83305e22a
fix: harden git workflow skills with better state handling ( #406 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-27 01:04:54 -07:00
da390a65a2
refactor: merge deepen-plan into ce:plan as automatic confidence check ( #404 )
2026-03-26 22:15:58 -07:00
Trevin Chow