recursive-mode

分类: 工具与效率 | 上传者: try-works | 下载: 0 | 版本: v1.0（最新）

用于分阶段实施、锁定工件、后期收据和持久内存维护的存储库工作流编排技能。在执行递归模式运行、恢复运行、锁定阶段或验证锁时使用。

更新日志: Source: GitHub https://github.com/try-works/recursive-mode

目录结构

当前层级: tree/main/

📁 .agent/
- 📄 PLANS.md 1.8 KB
📁 .codex/
- 📄 AGENTS.md 6.9 KB
📁 .recursive/
- 📁 memory/
  - 📁 archive/
    
    📄 .gitkeep 1 B
  - 📁 domains/
    
    📄 .gitkeep 1 B
  - 📁 episodes/
    
    📄 .gitkeep 1 B
  - 📁 incidents/
    
    📄 .gitkeep 1 B
  - 📁 patterns/
    
    📄 .gitkeep 1 B
  - 📁 skills/
    
    📁 availability/
    
    📄 .gitkeep 1 B
    
    📁 issues/
    
    📄 .gitkeep 1 B
    
    📁 patterns/
    
    📄 .gitkeep 1 B
    
    📄 delegated-verification-and-refresh.md 1.8 KB
    
    📄 phase8-skill-memory-promotion.md 1.4 KB
    
    📁 usage/
    
    📄 .gitkeep 1 B
    
    📄 skill-discovery-and-evaluation.md 1.6 KB
    
    📄 SKILLS.md 4.3 KB
  - 📄 MEMORY.md 5.2 KB
- 📁 run/
  - 📄 .gitkeep 1 B
- 📄 AGENTS.md 2.3 KB
- 📄 DECISIONS.md 1.1 KB
- 📄 README.md 5.7 KB
- 📄 RECURSIVE.md 200.6 KB
- 📄 STATE.md 1.6 KB
📁 agents/
- 📄 code-reviewer.md 6.1 KB
- 📄 implementer.md 6.3 KB
- 📄 openai.yaml 202 B
📁 docs/
- 📁 templates/
  - 📁 commands/
    
    📄 check-reusable-repo-hygiene.md 1.3 KB
    
    📄 recursive-closeout.md 2.5 KB
    
    📄 recursive-init.md 2.0 KB
    
    📄 recursive-lock.md 1.3 KB
    
    📄 recursive-review-bundle.md 3.0 KB
    
    📄 recursive-status.md 2.0 KB
    
    📄 recursive-subagent-action.md 3.1 KB
    
    📄 test-recursive-mode-smoke.md 3.4 KB
  - 📁 hooks/
    
    📄 hooks.json 400 B
    
    📄 run-hook.cmd 1.2 KB
    
    📄 session-start.ps1 3.4 KB
    
    📄 session-start.sh 3.3 KB
📁 references/
- 📁 bootstrap/
  - 📄 RECURSIVE.md 200.6 KB
- 📁 fixtures/
  - 📄 tiny-tasks-smoke-recipe.md 2.6 KB
- 📄 agents-block.md 6.9 KB
- 📄 artifact-template.md 70.3 KB
- 📄 local-first-web-app-checklist.md 1.6 KB
- 📄 plans-canonical.md 10.5 KB
📁 scripts/
- 📄 check-reusable-repo-hygiene.ps1 625 B
- 📄 check-reusable-repo-hygiene.py 6.3 KB
- 📄 install-recursive-mode.ps1 22.1 KB
- 📄 install-recursive-mode.py 21.6 KB
- 📄 install-recursive-mode.sh 363 B
- 📄 lint-recursive-run.ps1 739 B
- 📄 lint-recursive-run.py 107.1 KB
- 📄 recursive-closeout.ps1 1015 B
- 📄 recursive-closeout.py 21.4 KB
- 📄 recursive-init.ps1 16.3 KB
- 📄 recursive-init.py 10.9 KB
- 📄 recursive-lock.ps1 677 B
- 📄 recursive-lock.py 9.0 KB
- 📄 recursive-review-bundle.ps1 2.5 KB
- 📄 recursive-review-bundle.py 21.1 KB
- 📄 recursive-status.ps1 674 B
- 📄 recursive-status.py 96.0 KB
- 📄 recursive-subagent-action.ps1 4.3 KB
- 📄 recursive-subagent-action.py 9.4 KB
- 📄 test-recursive-mode-smoke.ps1 1.0 KB
- 📄 test-recursive-mode-smoke.py 112.9 KB
- 📄 verify-locks.ps1 733 B
- 📄 verify-locks.py 12.1 KB
📁 skills/
- 📁 recursive-debugging/
  - 📁 agents/
    
    📄 openai.yaml 229 B
  - 📄 SKILL.md 12.5 KB
- 📁 recursive-review-bundle/
  - 📁 agents/
    
    📄 openai.yaml 242 B
  - 📄 SKILL.md 2.7 KB
- 📁 recursive-spec/
  - 📁 agents/
    
    📄 openai.yaml 229 B
  - 📁 references/
    
    📄 patterns.md 3.8 KB
  - 📄 SKILL.md 4.9 KB
- 📁 recursive-subagent/
  - 📁 agents/
    
    📄 openai.yaml 255 B
  - 📄 SKILL.md 9.3 KB
- 📁 recursive-tdd/
  - 📁 agents/
    
    📄 openai.yaml 230 B
  - 📄 SKILL.md 9.9 KB
- 📁 recursive-worktree/
  - 📁 agents/
    
    📄 openai.yaml 233 B
  - 📄 SKILL.md 2.7 KB
📄 .gitattributes 199 B
📄 .gitignore 233 B
📄 AGENTS.md 6.9 KB
📄 LICENSE 11.1 KB
📄 README.md 10.8 KB
📄 SKILL.md 8.8 KB

SKILL.md

---
name: recursive-mode
description: 'Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.'
---

# recursive-mode

## Purpose

Use this skill to run the repository workflow defined in `/.recursive/RECURSIVE.md`.

This file is the installable entrypoint for the skill. It is not the canonical workflow spec.
For phase order, audit-loop rules, lock rules, addenda, late-phase receipts, state/decisions updates, and memory maintenance, follow `/.recursive/RECURSIVE.md`.

## Bootstrap

Before doing recursive-mode work, ensure the repo scaffold exists:

- `/.recursive/RECURSIVE.md`
- `/.recursive/STATE.md`
- `/.recursive/DECISIONS.md`
- `/.recursive/memory/MEMORY.md`
- `/.recursive/memory/skills/SKILLS.md`
- `/.recursive/memory/{domains,patterns,incidents,episodes,archive}/`
- `/.recursive/memory/skills/{availability,usage,issues,patterns}/`
- `/.recursive/run/`
- `/.codex/AGENTS.md` primary Codex bridge doc
- `/.agent/PLANS.md` bridge doc
- optional mirrored `AGENTS.md` docs if the repo already uses them

If any of those are missing or stale, the agent should bootstrap the repo automatically before continuing. Do not ask the user to run the bootstrap manually unless no supported Python or shell runtime is available in the environment. PowerShell is optional, not required.

Preferred bootstrap commands:

```bash
python ./scripts/install-recursive-mode.py --repo-root .
python3 ./scripts/install-recursive-mode.py --repo-root .
bash ./scripts/install-recursive-mode.sh --repo-root .
powershell -ExecutionPolicy Bypass -File ./scripts/install-recursive-mode.ps1 -RepoRoot .
pwsh -NoProfile -File ./scripts/install-recursive-mode.ps1 -RepoRoot .
```

Important boundary:

- `npx skills add ...` installs the skill package into agent directories.
- The target repository scaffold should then be created automatically on first recursive-mode use or via a wired session-start hook.
- Python and Bash paths are first-class and should work on macOS and Linux without PowerShell.
- Manual bootstrap commands are the fallback path, not the preferred normal UX.

## Read Order

1. Read `/.recursive/RECURSIVE.md`.
2. Read `/.codex/AGENTS.md` as the primary Codex bridge if present.
3. Read any other `AGENTS.md` copies only as mirrored bridge guidance if the repo uses them.
4. Read `/.agent/PLANS.md` as the primary Codex plans bridge if present.
5. Read `/.recursive/STATE.md`.
6. Read `/.recursive/DECISIONS.md`.
7. Read `/.recursive/memory/MEMORY.md`.
8. Load only the relevant memory docs under `/.recursive/memory/`.

If any bridge doc conflicts with `/.recursive/RECURSIVE.md`, follow `/.recursive/RECURSIVE.md`.

## Operational Surface

- Canonical run root: `/.recursive/run/<run-id>/`
- Canonical workflow spec: `/.recursive/RECURSIVE.md`
- Canonical state: `/.recursive/STATE.md`
- Canonical decisions ledger: `/.recursive/DECISIONS.md`
- Canonical memory router: `/.recursive/memory/MEMORY.md`

## Trigger Examples

- `Implement requirement '<run-id>'`
- `Run Recursive Phase 2 for .recursive/run/<run-id>/`
- `Resume requirement '<run-id>' after manual QA`
- `Verify locks for .recursive/run/<run-id>/`

## Utility Scripts

- `scripts/install-recursive-mode.py`
- `scripts/install-recursive-mode.ps1`
- `scripts/install-recursive-mode.sh`
- `scripts/recursive-init.py`
- `scripts/recursive-init.ps1`
- `scripts/recursive-status.py`
- `scripts/recursive-status.ps1`
- `scripts/lint-recursive-run.py`
- `scripts/lint-recursive-run.ps1`
- `scripts/recursive-review-bundle.py`
- `scripts/recursive-review-bundle.ps1`
- `scripts/recursive-subagent-action.py`
- `scripts/recursive-subagent-action.ps1`
- `scripts/recursive-lock.py`
- `scripts/recursive-lock.ps1`
- `scripts/verify-locks.py`
- `scripts/verify-locks.ps1`
- `scripts/check-reusable-repo-hygiene.py`
- `scripts/check-reusable-repo-hygiene.ps1`

## Subskills

- `skills/recursive-spec/SKILL.md`
- `skills/recursive-worktree/SKILL.md`
- `skills/recursive-debugging/SKILL.md`
- `skills/recursive-tdd/SKILL.md`
- `skills/recursive-review-bundle/SKILL.md`
- `skills/recursive-subagent/SKILL.md`

Use those subskills for their specialized discipline, but keep `/.recursive/RECURSIVE.md` as the single source of truth for the overall workflow contract.

For audited phases, the installed workflow requires `draft -> audit -> repair -> re-audit -> pass -> lock`, with `Audit: PASS` required before Coverage/Approval may pass.
Treat `## Worktree Diff Audit` as phase-scoped: Phase 2 owns planning completeness plus expected product/worktree paths, Phase 3-4 own actual product/worktree drift, Phase 6 owns `/.recursive/DECISIONS.md`, Phase 7 owns `/.recursive/STATE.md`, and Phase 8 owns `/.recursive/memory/**`.
For Phase 3, declare `TDD Mode: strict|pragmatic`. Strict mode requires concrete RED and GREEN evidence paths. Pragmatic mode requires an explicit exception rationale plus compensating evidence.
For Phase 5, declare `QA Execution Mode: human|agent-operated|hybrid`. Do not fake human sign-off for agent-operated QA, and do not omit sign-off for human or hybrid QA.
For delegated review, prefer `scripts/recursive-review-bundle.py` or `scripts/recursive-review-bundle.ps1` so Phase 3.5 records a canonical `Review Bundle Path`.
If meaningful subagent work contributes to a phase, record it under `/.recursive/run/<run-id>/subagents/` and verify the action record against actual files, actual diffs, and actual recursive artifacts before accepting it. For review/audit delegation, prefer a stable reviewed artifact for `Current Artifact` rather than a mutable draft receipt.
Audited phases must record `Subagent Capability Probe`, `Delegation Decision Basis`, `## Subagent Contribution Verification`, and `## Requirement Completion Status`.
When subagents are available and the context bundle is complete, delegated audit/review is the default path. If the controller still uses `Audit Execution Mode: self-audit`, record a concrete `Delegation Override Reason`.
Use the stronger requirement disposition fields in `## Requirement Completion Status`: `Changed Files`, `Implementation Evidence`, `Verification Evidence`, `Deferred By`, `Scope Decision`, `Blocking Evidence`, and `Addendum` as appropriate to the chosen status.
Do not mark `implemented` or `verified` without concrete `Changed Files`. Do not mark `verified` without distinct verification evidence.
Treat addenda as authoritative effective inputs. When relevant addenda exist, list them under `Inputs`, re-read them in `## Effective Inputs Re-read`, and reconcile them in `## Earlier Phase Reconciliation`.
Review bundles should include relevant addenda automatically, and the written Phase 3.5 review should cite bundle-grounded upstream artifacts, addenda, and changed files or code refs in the review narrative.
`00-worktree.md` is the source of truth for diff basis. Record baseline type/reference, comparison reference, normalized baseline/comparison, and normalized diff command; do not silently improvise a different basis later.
Use Phase 8 to update skill memory under `/.recursive/memory/skills/` when the run teaches the repo something durable about skill availability, fit, delegated-review quality, or skill-discovery outcomes.
Phase 8 should also capture run-local skill usage before promoting any lesson into durable memory.
If the run plans delegated review, review bundles, or smoke-harness portability work, read `/.recursive/memory/skills/SKILLS.md` and the relevant skill-memory shards before planning or auditing.
If the run needs a specialized capability that is not already available, prefer the `find-skills` skill when it exists. Otherwise use the Skills CLI directly (`npx skills find`, `npx skills add`, `npx skills check`, `npx skills update`) and record the result when skill usage is relevant.
Diff audit ignores incidental runtime byproducts such as `__pycache__/`, `*.pyc`, `.pytest_cache/`, `.mypy_cache/`, and `.ruff_cache/` unless the repo intentionally tracks them.
Treat Phase 6, Phase 7, and Phase 8 receipts as concise delta receipts that point to the final control-plane docs instead of restating large sections.
Use `scripts/recursive-lock.py` or `scripts/recursive-lock.ps1` as the normal locking path instead of manually editing `Status`, `LockedAt`, and `LockHash`.
On Windows, run Node/Vite/Vitest commands from the real worktree path rather than `subst` or mapped-drive aliases.
When evaluating or building browser-local apps, consult `references/local-first-web-app-checklist.md` for common import/persistence/QA edge cases.
If the repository being improved is itself a reusable skill/workflow repo, do not commit current-session run folders, evidence logs, review bundles, subagent action records, or temp-path references unless they are intentional fixtures; use `scripts/check-reusable-repo-hygiene.py` or `scripts/check-reusable-repo-hygiene.ps1` before calling the repo clean.

登录后下载/点赞/收藏 ❤ 18 | ★ 0

recursive-mode

目录结构

SKILL.md

举报内容

提示