Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add me-cedric/agent-compass --skill harness-loopgit clone --depth 1 https://github.com/me-cedric/agent-compassWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/me-cedric/agent-compass/harness-loop)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/harness-loop"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/harness-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/me-cedric/agent-compass/harness-loop"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/harness-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00762 |
| Opus 5.5 | $0.00020 | $0.00305 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
harness-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harness-loop
Set up
State these items before you start. Ask only about an item that blocks safe work.
- Goal: one sentence.
- Check: one command that proves the goal.
- Stop condition: the check passes, the turn cap is reached, or a blocker stops the work.
- Turn cap: 20 turns unless the user says another number. Never raise the cap yourself.
- 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
- Read the repository rules, the project memory and the specs that the goal touches.
- For work on more than one file, run the
deliverworkflow (.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 thescout,workerandrevieweragents. - Do one phase in each turn.
- After each phase, read your diff and run the check.
- Fix a failure that you introduced before you start the next phase.
- Write the result in the progress file.
- At the cap, report "partial" with the blocker. Do not continue.
Parallel work
- Run 2 workers at most. Give them files that do not overlap.
- Before the first edit in a worktree or a new branch, run
git log --oneline main..HEADandgit log --oneline HEAD..main. - If the branch is behind and has no commits of its own, run
git merge --ff-only main. - If the branch is behind and has its own commits, tell the parent. Do not rebase.
- If the user allows commits, commit each finished piece. A session that dies loses uncommitted work.
- Stay inside the files that your task names.
- 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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 64 lines · 50 tokens per session scan A 5db08e561fa8
harness-loop is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 762 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other skills, from other repositories
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
founder-coach
Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO calendar audits, leadership style evolution, blind spot identification, imposter syndrome, founder mental health, and succession planning. Use when a founder feels…
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
meetings
Context for the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks and calendar cache live, what the lifecycle states mean, how the app's agents are driven. Load when asked about a meeting's notes or action items, or when touching the meetings app data dir.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.