- frontend-architect: opus → sonnet (executes planner's plan)
- backend-architect: opus → sonnet (executes planner's plan)
- code-reviewer: sonnet → opus (deep reasoning for vulnerability/architecture analysis)
- prompt-engineer: marked as optional (only for projects with LLM integration)
Principle: planner does deep thinking, implementation agents execute the plan.
Opus reserved for: planning, security audit, code review.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Agents:
- Add YAML frontmatter (model, tools) to all 7 existing agents
- New agents: planner (opus), build-error-resolver (sonnet), loop-operator (sonnet)
Skills:
- search-first: research before building (Adopt/Extend/Compose/Build)
- verification-loop: full quality gate pipeline (Build→TypeCheck→Lint→Test→Security→Diff)
- strategic-compact: when and how to run /compact effectively
- autonomous-loops: 6 patterns for autonomous agent workflows
- continuous-learning: extract session learnings into instincts
Hooks:
- Profile system (minimal/standard/strict) via run-with-profile.sh
- config-protection: block linter/formatter config edits (standard)
- suggest-compact: remind about /compact every ~50 tool calls (standard)
- auto-tmux-dev: suggest tmux for dev servers (standard)
- session-save/session-load: persist and restore session context (Stop/SessionStart)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove all .github references (removed in 6c644dd but docs still referenced)
- Rewrite review-pr skill to use Gitea API instead of gh CLI
- Add gitea-pr.sh helper for Gitea API calls (view/diff/files/comments)
- Update project structure tree: add scripts/, .woodpecker.yml, ci-cd.md,
status-update-checklist.md, commit-docs-reminder.sh, RESEARCH-SDD-TOOLS.md
- Fix skills count 14 → 15 (add create-skill to DOCS.md)
- Remove .github references from CONTRIBUTING.md, SECURITY.md, init-project
- Add GITEA_TOKEN to .env.example
- Update CI/CD placeholder in RECOMMENDATIONS.md to Woodpecker
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two modes: Create (gather requirements, generate SKILL.md) and Improve
(diagnose existing skill against best practices, propose changes).
Includes bundled references for frontmatter spec and writing guide.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Comparative analysis of GitHub's spec-kit and lee-to/ai-factory
for spec-driven development workflows and iterative AI coding.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replaced narrow .env.local / .env.*.local rules with .env.* to prevent
accidental commit of .env.production, .env.development, .env.staging, etc.
Explicitly allowlisted .env.example so it remains tracked.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
deploy.sh:
- add step 3: nginx config apply with Webuzo/standard detection
- configurable via NGINX_CONF_SRC and NGINX_DOMAIN variables
setup-project.sh:
- move add_header to server block level (inside location / they are
overridden by Webuzo's regex location and never sent)
- detect Webuzo nginx binary (/usr/local/apps/nginx/sbin/nginx)
instead of hardcoded systemctl reload nginx
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New specialized agent for technical writing, documentation standards,
and generating docs from code. Includes Diataxis framework, severity-based
review checklists, code-to-docs patterns, and quality metrics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a PreToolUse Bash hook that reminds AI agents to verify
status-update-checklist.md before running git commit. Also adds
the corresponding constraint to RULES.md section 3.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
