메뉴
Write a custom control policy only when current runtime composition APIs cannot express it.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/tangle-network/agent-runtime --skill loop-writer명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | loop-writer |
| description | Write a custom control policy only when current runtime composition APIs cannot express it. |
Use this only for a control policy that the shipped high-level APIs cannot express.
Read docs/canonical-api.md, current exports, the implementation, and the nearest test before writing code.
Do not copy signatures from this skill.
| Need | Existing path |
|---|---|
| One product chat turn | handleChatTurn(...) |
| One task or bounded multi-turn task | runAgentTask(...) or runAgentTaskStream(...) |
| Two or more actors taking turns | defineConversation(...) and runConversation(...) |
| A driver coordinating workers | supervise(...) or superviseSurface(...) |
| Parallel or fixed composition | fanout(...), pipeline(...), panel(...), verify(...), or loopUntil(...) |
| Parallel repository workers with isolated branches | worktreeFanout(...) |
| Repeated work in a graded tool environment | runAgentic(...) |
| Equal-budget comparison over that environment | runBenchmark(...) |
| Low-level round policy with custom planning and stopping | runAgentRounds(...) |
If an existing row fits, use it and stop. Do not create another wrapper solely to rename inputs or results.
A custom loop has five explicit parts:
task -> plan work -> execute attempts -> check outcomes -> continue or stop
Keep ownership separate:
The driver must not mutate product state while planning. An LLM score must not override failed builds, tests, missing evidence, denied permissions, or service errors.
Model every terminal and resumable state explicitly:
Use stable run, attempt, task, and parent IDs. Persist the accepted artifact, every attempted artifact identity, spend, and final reason. Resume from durable facts, not an in-memory counter or summary alone.
Steering is a typed input to a running or replacement attempt. Record who sent it, why, which evidence motivated it, whether delivery succeeded, and which attempt consumed it.
Questions are explicit events. Route them to the responsible parent or user, preserve unanswered blockers, and fail closed when a required answer is unavailable. Do not bury a permission request in free-form worker output.
Give parallel workers isolated state unless shared mutation is the point of the task. For repository changes, use one worktree per worker and explicit merge outcomes. For external writes, use idempotency keys and product-owned transactions.
Recursive supervisors use the same budget, cancellation, trace, question, and completion contracts at every depth. Do not grant a child more authority than its parent.
Cover:
The change is complete when the public entrypoint is smaller than the policy it replaces, all states above are observable, a real task exercises the custom behavior, and package typecheck, tests, build, docs, and package verification pass.
critical-audit when the loop changes a public contract or authority boundary.eval-engineering when the loop's stopping condition needs a new evaluation case.verify before publishing the package.