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 agentmods add skills/keesan12/martin-loop/martinloop-governnpx skills add Keesan12/martin-loop --skill martinloop-governgit clone --depth 1 https://github.com/Keesan12/martin-loopWrote 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/keesan12/martin-loop/martinloop-govern)<a href="https://agentmods.dev/skills/keesan12/martin-loop/martinloop-govern"><img src="https://agentmods.dev/badge/skills/keesan12/martin-loop/martinloop-govern.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00298 |
| Opus 5 | $0.00015 | $0.00149 |
| Sonnet 5 | $0.00006 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
martinloop-govern 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 3d 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.
What it actually says
Govern With MartinLoop
Use MartinLoop as the execution-control and evidence layer around the coding agent. Preserve the user's requested scope and never replace verifier evidence with an agent assertion.
Workflow
- Call
martin_doctorto confirm the environment is ready. - Call
martin_estimateto expose budget and cost posture before spend. - Call
martin_planto define the bounded objective, files, and verification. - Call
martin_preflightand resolve blocking contract issues before execution. - Call
martin_runonly after preflight accepts the contract. - Call
martin_dossierafter the run and inspect its evidence.
Outcome Rules
- Report
VERIFIEDonly with verifier-backed completion evidence. - Treat
STOPPEDas a real enforced boundary and report its recorded reason. - Treat
NEEDS_REVIEWas unresolved evidence, never successful completion. - Preserve the dossier or Verified Handoff as the completion record.
- Never weaken a gate, increase a budget, or approve protected work without authorization.
- Let the coding agent or provider select its model unless the user explicitly overrides it.
First Task
For a low-risk trial, govern a small repository change with a real verifier and inspect the resulting dossier.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 31 lines · 29 tokens per session scan A ab2b753f79bd
martinloop-govern is a skill published in the GitHub repository Keesan12/martin-loop (47 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 298 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
decision-rubric
Apply a rigorous decision rubric when asking the user for a non-trivial design, architectural, or policy choice via AskUserQuestion. Replaces shallow "do you agree with the author's recommendation?" prompts with a full problem statement → industry research → 3-4 options with tradeoffs → recommendation +…
ai-sdlc-governance
AI-SDLC project governance rules, workflow expectations, and pre-commit checklist. Loaded automatically at session start.
debug-task
Debug autonomous /task execution — query taskruns state, phase context/costs, trace tool decisions in audit.jsonl, and check app logs for errors. Use when a task fails, gets stuck, escalates, or behaves unexpectedly.
debug-leashd
Debug leashd issues by querying SQLite sessions/messages, reading audit.jsonl tool decisions, and parsing logs/app.log application events. Use when something doesn't work as expected, to trace requests, inspect approvals, or diagnose bugs.
telegram-harness
Run leashd's live tmux+Telegram verification harness in scripts/harness/ — a fake Telegram Bot API plus a real Engine/TmuxAgent/MultiConnector wired like runmulti. Inject messages, slash commands, and inline-button taps and observe the exact outbound streaming/approval/plan/task timeline. Use to reproduce or verify…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…