martinloop-govern

martinloop-govern is a skill for Claude Code, Codex from Keesan12/martin-loop. It costs 29 tokens per session (298 once invoked), scanned A, original, Apache-2.0.

A workflow for controlling coding-agent implementation with MartinLoop, including planning, limits, preflight checks, recovery, and evidence from verifiers. It treats a verified result, a stop, and unresolved review as different outcomes.

In plain words
What is it for?
Use it to check the environment, estimate and plan work, validate the execution contract, run the bounded task, and inspect the final evidence dossier or handoff.
Why use it?
It prevents an agent from being treated as successful without evidence and keeps the requested work within an agreed scope and budget.

Skill for Claude CodeCodex

Part of the martinloop plugin — 1 skill, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/keesan12/martin-loop/martinloop-govern
Any agent
npx skills add Keesan12/martin-loop --skill martinloop-govern
Clone the repo
git clone --depth 1 https://github.com/Keesan12/martin-loop

Made for: Claude Code, Codex.

Or install martinloop, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for martinloop-govern

README.md
[![agentmods](https://agentmods.dev/badge/skills/keesan12/martin-loop/martinloop-govern.svg)](https://agentmods.dev/skills/keesan12/martin-loop/martinloop-govern)
Your own site
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash ab2b753f79bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/martinloop/skills/martinloop-govern/SKILL.md · 31 lines

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

  1. Call martin_doctor to confirm the environment is ready.
  2. Call martin_estimate to expose budget and cost posture before spend.
  3. Call martin_plan to define the bounded objective, files, and verification.
  4. Call martin_preflight and resolve blocking contract issues before execution.
  5. Call martin_run only after preflight accepts the contract.
  6. Call martin_dossier after the run and inspect its evidence.

Outcome Rules

  • Report VERIFIED only with verifier-backed completion evidence.
  • Treat STOPPED as a real enforced boundary and report its recorded reason.
  • Treat NEEDS_REVIEW as 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.

Files

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.

Changes

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.

  1. 3d ago First seen · 31 lines · 29 tokens per session scan A ab2b753f79bd

Subscribe to this mod's changes

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.

Related

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-framework/ai-sdlc · 168 tokens

ai-sdlc-governance

AI-SDLC project governance rules, workflow expectations, and pre-commit checklist. Loaded automatically at session start.

ai-sdlc-framework/ai-sdlc · 31 tokens

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.

vmehera123/leashd · 51 tokens

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.

vmehera123/leashd · 49 tokens

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…

vmehera123/leashd · 90 tokens

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…

lawve-ai/awesome-legal-skills · 85 tokens