Applies triage docs 016-019 — merges upstream's structural refactor with
local's fork-specific additions.
README:
- Drop entries for locally-removed agents (dhh/kieran-rails, design/*,
ankane-readme-writer, performance-oracle, security-sentinel,
data-migration-expert)
- Add local custom skills (ce-john-voice, ce-hugo-blog-publisher,
ce-story-lens, ce-essay-outline, ce-essay-edit, ce-excalidraw-png-export,
ce-sync-confluence, ce-jira-ticket-writer, ce-upstream-merge,
ce-proof-push, ce-ship-it, ce-weekly-shipped) under appropriate sections
- Add local custom agents (ce-design-conformance-reviewer,
ce-tiangolo-fastapi-reviewer, ce-zip-agent-validator, ce-lint,
ce-python-package-readme-writer)
- Add ce-fastapi-style, ce-python-package-writer to Development Frameworks
- Preserve "privacy/compliance angle" suffix on ce-data-integrity-guardian
- Add ce-previous-comments-reviewer entry (present in code, was missing
from README)
- Update component counts to match actual filesystem (47 agents, 50 skills)
ce-brainstorm: insert Deploy wiring flag paragraph once in Phase 2
approach presentation (local carried this edit; deduped the accidental
double-insertion from the local diff).
ce-plan: insert Deploy wiring check bullet in "Every plan should contain"
list and in Phase 1 Repo Scan Signals section.
ce-work: insert "Did I add new env vars or config fields?" row in the
Phase 2 pattern-sensitive check table.
ce-work shipping-workflow: insert "If new env vars added to backend
config, deploy values files updated in same PR" line in pre-PR checklist.
All deploy-wiring additions reference
docs/solutions/deployment-issues/missing-env-vars-in-values-yaml.md
(note: the referenced solution doc doesn't exist yet — flagged for
follow-up).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Surface deferred implementation questions and scope boundaries
- Use per-unit Patterns and Verification fields for task execution
- Add execution strategy: inline, serial subagents, or parallel
- Reframe Swarm Mode as Agent Teams with opt-in requirement
- Make tool references platform-agnostic
- Remove plan checkbox editing during execution
* feat: make PR/commit attribution specific to model, harness, and plugin version
Replace generic "Generated with Claude Code" footer with dynamic attribution
that includes the actual model name, harness tool, and plugin version. LLMs
fill in their own values at commit/PR time. Subagents are explicitly
instructed to do the same.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: format attribution substitution guide as table
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: rename badge to "Compound Engineering v[VERSION]"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add context window and thinking level to attribution
Separate MODEL into MODEL, CONTEXT, and THINKING placeholders
so each detail is its own table row and easier to read.
Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
* style: badge on its own line, model details on next line in PR template
Co-Authored-By: Claude Opus 4.6 (1M context, extended thinking) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move all 27 command .md files from commands/ to skills/*/SKILL.md
format. Claude Code 2.1.3+ merged commands and skills - both create
slash commands and work identically. Skills add optional features
like supporting files and automatic context loading.
- commands/ce/*.md -> skills/ce-*/SKILL.md
- commands/workflows/*.md -> skills/workflows-*/SKILL.md
- commands/*.md -> skills/*/SKILL.md
- Update plugin.json and marketplace.json descriptions
- Update CLAUDE.md directory structure docs
- Update deploy-docs and generate_command references
Fixes#116
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
