gendesign/.claude/agents
lekss361 f36da624fe chore(claude): harden autonomous multi-agent prompts (Path B)
Fix structural causes of autonomous-window underperformance vs single-window
orchestration — persona prompts were thin pointers that deferred conventions
to unread files and dead-ended every imperfect PR into human review.

- Inline-load conventions: каждый work-тик MANDATORY-читает полный
  backend/frontend-engineer.md + rules (был optional pointer, который cost-rule
  отучал читать). Cost-saving "не строй контекст" сужен до idle-тиков явно.
- Auto-fix loop: reviewer FIX -> status/needs-fix (assignee остаётся worker),
  worker сам подхватывает свой PR и пушит fixup в ту же ветку. blocked+needs-human
  зарезервирован под BLOCK (security/data-loss) или 3x fix-fail (+ fix-attempt cap).
  QA feature_regression -> needs-fix аналогично. FSM-таблица обновлена.
- Fat issue template: auto-analyst делает mandatory code archeology (Grep/Read)
  и пишет Files/сигнатуры/Acceptance/Risk (формат tech-analyst) — issue это
  единственный канал к worker'у.
- Model resolution doc: model: frontmatter мёртв в standalone /loop-окне
  (модель = модель окна); reviewer-окно запускать в Opus 4.8 осознанно.
- Drift fix: stale-claim cleanup помечен implemented (cron stale-claims.yml в
  проде, #610-612); отмечен gap pause-bots vs cleanup.

Новый label status/needs-fix создать в Forgejo до первого запуска auto-fix loop.
2026-05-29 16:38:23 +03:00
..
deep-review-phases chore(claude-config): align with 2026 best practices (#495) 2026-05-24 08:48:42 +00:00
_autonomous_pickup.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
auto-analyst.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
auto-backend.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
auto-code-reviewer.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
auto-frontend.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
auto-qa-tester.md chore(claude): harden autonomous multi-agent prompts (Path B) 2026-05-29 16:38:23 +03:00
backend-engineer.md refactor(claude): split 700-line CLAUDE.md into path-scoped .claude/rules/ (#188) 2026-05-15 23:06:33 +03:00
code-reviewer.md chore(claude-config): align with 2026 best practices (#495) 2026-05-24 08:48:42 +00:00
database-expert.md refactor(claude): split 700-line CLAUDE.md into path-scoped .claude/rules/ (#188) 2026-05-15 23:06:33 +03:00
deep-code-reviewer.md chore(claude-config): align with 2026 best practices (#495) 2026-05-24 08:48:42 +00:00
devops-engineer.md refactor(claude): split 700-line CLAUDE.md into path-scoped .claude/rules/ (#188) 2026-05-15 23:06:33 +03:00
frontend-engineer.md refactor(claude): split 700-line CLAUDE.md into path-scoped .claude/rules/ (#188) 2026-05-15 23:06:33 +03:00
qa-tester.md chore(claude-config): align with 2026 best practices (#495) 2026-05-24 08:48:42 +00:00
tech-analyst.md chore(claude-config): align with 2026 best practices (#495) 2026-05-24 08:48:42 +00:00