harness-loop
/harness-loop
Run a large goal as a loop with one check, a progress file on disk and a turn cap. Uses the deliver workflow for multi-file work. Use when the user asks you to keep going until a big goal is finished.
- Author
- me-cedric ↗
- Repository
- Shipyard ↗
- Licence
- MIT
- Last repository change
- 12.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 12.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Run a large goal as a loop with one check, a progress file on disk and a turn cap. Uses the deliver workflow for multi-file work. Use when the user asks you to keep going until a big goal is finished.
Original author description
Run a large goal as a loop with one check, a progress file on disk and a turn cap. Uses the deliver workflow for multi-file work. Use when the user asks you to keep going until a big goal is finished.
How it works
- Set up
- Loop
- Parallel work
- Worktree fence
- Safety
- Handoff
SKILL.md preview
--- name: harness-loop description: Run a large goal as a loop with one check, a progress file on disk and a turn cap. Uses the deliver workflow for multi-file work. Use when the user asks you to keep going until a big goal is finished. risk_level: medium writes_files: true requires_tools: [git] disable-model-invocation: true --- # harness-loop ## Set up State these items before you start. Ask only about an item that blocks safe work. 1. Goal: one sentence. 2. Check: one command that proves the goal. 3. Stop condition: the check passes, the turn cap is reached, or a blocker stops the work. 4. Turn cap: 20 turns unless the user says another number. Never raise the cap yourself. 5. Out of scope: what you will not touch. Write the progress file `.agents/progress/<goal-slug>.md`. It holds the five items above, the done list, the next step and the blockers. Read it at the start of each turn. A new context resumes from this file. ## Loop 1. Read the repository rules, the project memory and the specs that the goal touches. 2. For work on more than one file, run the `deliver` workflow (`.claude/workflows/deliver.js`) with the goal as args. The workflow plans, then splits the work into 2 file groups at most. Workers build. A reviewer checks in a fresh context. Fixes take 2 rounds at most. Without workflow support, do the same steps with the `scout`, `worker` and `reviewer` agents. 3. Do one phase in each turn. 4. After each phase, read your diff and run the check. 5. Fix a failure that you introduced before you start the next phase. 6. Write the result in the progress file. 7. At the cap, report "partial" with the blocker. Do not continue. ## Parallel work 1. Run 2 workers at most. Give them files that do not overlap. 2. Before the first edit in a worktree or a new branch, run `git log --oneline main..HEAD` and `git log --oneline HEAD..main`. 3. If the branch is behind and has no commits of its own, run `git merge --ff-only main`. 4. If the branch is behind and has its own commits, tell the parent. Do not rebase. 5. If the user allows commits, commit each finished piece. A session that dies loses uncommitted work. 6. Stay inside the files that your task names. 7. Do not remove a worktree because it looks finished. Wait for the signal of the orchestrator. ## Worktree fence The desktop app fences each subagent. A hook refuses Edit, Write and git commands that target another worktree. 1. Run the shared steps in the session worktree: merge, screenshots, land. 2. A reviewer of a lane worktree calls `EnterWorktree` with the lane path first. 3. Read a saved subagent report for "the hook refused" notes before you trust it. A refusal appears in the notes, not as a failure. ## Safety - Do not commit, push, open a PR, deploy, publish, write to production or run a migration on production without approval. - Use only commands that exist: in `package.json`, in a Makefile, or in the documented command list. Do not invent one. - Prefer a narrow fix to a broad rewrite. ## Handoff Give the goal, the files changed, each command with its result, the risks and the next step.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · me-cedric/Shipyard | 90 | MIT |
| hanspeterdietiker/open-agent-skills | 90 | MIT |
Database snapshot: 13.11.2026 · package version 8a9a0418f76b (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100meta-agent-harness
Use when a goal needs a bounded agentic loop: compile a verifiable plan, execute one task at a time until checks pass. - 100goal-harness
Turn a fuzzy task into a goal with five elements — a concrete outcome, a verification that proves it, constraints that fence the scope, an iteration policy, and error handling — plus a rubric, then run it as an executor-reviewer loop that stops only when the rubric passes or a… - 100loop-designer
Compile a goal into a durable, file-backed agent loop — a .loop/<name>/ charter any coding agent (Claude Code, Codex, Gemini, Grok) can execute unattended. Use when the user wants to "build a loop", "design a loop", "run X continuously/24-7", "make an agent keep working on Y",… - 100agent-harness
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until… - 90goal-loop
Run a task as a goal loop. Write a contract (goals, exit criteria, checks, budget), work, verify with an independent agent, repeat on FAIL until PASS or budget. Use for "goal loop", "verify until done", or exit criteria plus a verifier. - 86lifecycle-loop
Turn the request into a goal card, run its checks, and loop test-first work and build-and-test until every check passes or progress stalls. Use at the start of a task, whenever a check fails, and when a goal tool or a goal-verification prompt asks whether you are done.