796bea75b7
fix(agents): rename .agent.md to .md for VS Code Copilot tool access ( #846 )
...
Co-authored-by: Trevin Chow <trevin@trevinchow.com >
2026-05-21 00:18:17 -07:00
9b45a83d7e
feat(ce-compound): add mode:headless for non-interactive use ( #813 )
2026-05-10 12:50:12 -07:00
5139ff13e9
fix(ce-work-beta): replace semicolon pre-resolution with single-command form ( #758 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-05 12:01:22 -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
9539bf045d
fix(ce-compound, ce-sessions): remove bash parameter expansion from ! backtick ( #752 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-02 10:44:09 -07:00
d69a772bb8
fix(review): queue reviewers when subagent slots fill ( #716 )
2026-04-28 13:01:10 -07:00
1f0a77bcc1
fix(skills): replace shell antipatterns blocked by permission check ( #711 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-28 00:14:27 -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
5952b20d7f
fix(skills): replace case statements blocked by permission check ( #701 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-26 14:22:20 -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
6514b1fce5
feat(ce-ideate): subject gate, surprise-me, and warrant contract ( #671 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-24 02:04:21 -07:00
7ddfbed33b
feat(pi): first-class support via pi-subagents + pi-ask-user ( #651 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-22 10:26:29 -07:00
13f95ba639
fix(skills): cap skill descriptions at harness limit ( #643 )
2026-04-21 21:56:15 -07:00
ff0eee391e
refactor(ce-brainstorm): make doc review opt-in in Phase 4 handoff ( #633 )
2026-04-21 16:28:20 -07:00
4c57508c1a
refactor(agents): flatten agents directory ( #621 )
2026-04-21 02:35:21 -07:00
d359cc7e2f
fix(question-tool): stop silent skips when tool looks unavailable ( #620 )
2026-04-21 01:27:52 -07:00
3ed4a4fa0f
feat(codex): native plugin install manifests + agents-only converter ( #616 )
2026-04-20 19:44:25 -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
2aee4d4203
fix(ce-release-notes): backtick-wrap <skill-name> token in description ( #603 )
2026-04-19 00:38:15 -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
e7cf0ae957
feat(proof, ce-brainstorm, ce-plan, ce-ideate): HITL review-loop mode ( #580 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-04-16 23:14:33 -07:00
c89f18a115
fix(ce-pr-description): hand off PR body via temp file ( #581 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-04-16 22:47:49 -07:00
4ccadcfd3f
fix(resolve-pr-feedback): unblock /loop scheduling ( #582 )
2026-04-16 22:28:52 -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
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
d37f0ed16f
feat(ce-update): add plugin version check skill and ce_platforms filtering ( #532 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-08 00:09:02 -07:00
949bdef909
fix(review,work): omit mode parameter in subagent dispatch to respect user permissions ( #522 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-06 12:12:31 -07:00
fd562a0d02
feat(ce-plan): reduce token usage by extracting conditional references ( #489 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-02 01:55:53 -07:00
1962f546b5
fix(ce-plan): route confidence-gate pass to document-review ( #462 )
2026-03-31 00:21:48 -07:00
615ec5d3fe
feat(ce-plan): strengthen test scenario guidance across plan and work skills ( #410 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-27 09:55:24 -07:00
da390a65a2
refactor: merge deepen-plan into ce:plan as automatic confidence check ( #404 )
2026-03-26 22:15:58 -07:00
b30288c44e
feat: add project-standards-reviewer as always-on ce:review persona ( #402 )
2026-03-26 19:20:15 -07:00
0877b693ce
fix: add strict YAML validation for plugin frontmatter ( #399 )
2026-03-26 14:07:28 -07:00
506ad01b4f
fix: replace broken markdown link refs in skills ( #392 )
2026-03-26 11:57:19 -07:00
27b9831084
feat: add new onboarding skill to create onboarding guide for repo ( #384 )
2026-03-25 21:30:09 -07:00
efa798c52c
feat: improve commit-push-pr skill with net-result focus and badging ( #380 )
2026-03-25 16:28:47 -07:00
18d22afde2
feat: redesign document-review skill with persona-based review ( #359 )
2026-03-24 01:51:22 -07:00
affba1a6a0
feat: improve reproduce-bug skill, sync agent-browser, clean up redundant skills ( #333 )
2026-03-21 19:49:12 -07:00
52df90a166
feat: make skills platform-agnostic across coding agents ( #330 )
2026-03-21 17:35:22 -07:00
eaaba1928b
feat: add claude-permissions-optimizer skill ( #298 )
2026-03-18 01:18:27 -07:00
f47f829d81
feat: migrate repo releases to manual release-please ( #293 )
2026-03-17 17:58:13 -07:00
a83e11e982
fix: review fixes — stale refs, skill counts, and validation guidance
...
- Fix -plan.md → -beta-plan.md in ce:plan-beta post-generation question
- Remove stale brainstorm doc reference from solutions doc
- Update plugin.json and marketplace.json skill counts (42 → 44)
- Add generic beta skill validation guidance to AGENTS.md and solutions doc
2026-03-17 10:39:02 -07:00
72d4b0dfd2
fix: add disable-model-invocation to beta skills and refine descriptions
...
Beta skills now use disable-model-invocation: true to prevent accidental
auto-triggering. Descriptions written as future stable descriptions with
[BETA] prefix for clean promotion. Updated solutions doc and AGENTS.md
promotion checklist to include removing the field.
2026-03-17 10:33:01 -07:00
ac53635737
fix: beta skill naming, plan file suffixes, and promotion checklist
...
- Beta plans use -beta-plan.md suffix to avoid clobbering stable plans
- Fix internal references in beta skills to use beta names consistently
- Add beta skills section to AGENTS.md with promotion checklist
2026-03-17 10:33:01 -07:00
e4ee77aa1e
Merge pull request #281 from EveryInc/fix/research-agents-prefer-native-tools
...
fix: research agents to prefer native tools over shell
2026-03-16 22:26:12 -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
82c1fe86df
chore: remove deprecated workflows:* skill aliases ( #284 )
...
* docs: capture codex skill prompt model
* fix: align codex workflow conversion
* chore: remove deprecated workflows:* skill aliases
The workflows:brainstorm, workflows:plan, workflows:work, workflows:review,
and workflows:compound aliases have been deprecated long enough. Remove them
and update skill counts (46 → 41) across plugin.json, marketplace.json,
README, and CLAUDE.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
---------
Co-authored-by: Trevin Chow <trevin@trevinchow.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-16 23:19:03 -05:00
462456f582
docs(plugin): move compound-engineering instructions into AGENTS
2026-03-15 14:57:35 -07:00
Brian Paden
Trevin Chow
David A. Lee
Kieran Klaassen
David Gerő