A Claude Code plugin that learns a repository's coding patterns from Git history and flags code that looks out of place. It includes skills, an MCP server for agent access, and an optional pre-write check that does not block edits.

For checking code, reviewing pull requests, setting up repository checks, writing rules, and suggesting rules based on Git history.

It gives AI-generated changes a way to follow the project's existing style instead of applying unrelated patterns.

argot — Plugin for Claude Code by get-tmonier

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.

Clone the repo

git clone --depth 1 https://github.com/get-tmonier/argot

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/get-tmonier/argot/argot/github.svg)](https://agentmods.dev/plugins/get-tmonier/argot/argot)

Your own site

<a href="https://agentmods.dev/plugins/get-tmonier/argot/argot"><img src="https://agentmods.dev/badge/plugins/get-tmonier/argot/argot/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/get-tmonier/argot/argot"><img src="https://agentmods.dev/badge/plugins/get-tmonier/argot/argot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 7 skills, 1 hook, 1 MCP server cost 851 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

argot 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 1mo 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.

.claude-plugin/plugin.json · 32 lines

What it actually says

{
  "name": "argot",
  "displayName": "argot",
  "version": "0.2.129",
  "description": "A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.",
  "author": {
    "name": "Damien Meur",
    "url": "https://tmonier.com"
  },
  "homepage": "https://argot.tmonier.com",
  "repository": "https://github.com/get-tmonier/argot",
  "license": "MIT",
  "keywords": [
    "guardrail",
    "code-quality",
    "linter",
    "voice",
    "ai-code",
    "git"
  ],
  "mcpServers": {
    "argot": {
      "command": "argot",
      "args": [
        "mcp",
        "--repo",
        "."
      ]
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 7 skills, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 851 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json 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.

marketplace.json 738 B

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.

1mo ago Changed 8e4503c3e114
1mo ago First seen · 32 lines scan A c5ddec7a91f1

Subscribe to this mod's changes

argot is a plugin published in the GitHub repository get-tmonier/argot (51 stars, last pushed 15d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Code review ci cli code-quality coding-style developer-tools

roam-code

Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.

Cranot/roam-code · not measured

nullius

Evidence Anchors for agent-written design docs: load-bearing claims about existing code carry citations a deterministic checker re-verifies. Includes the authoring skill and a [false-premise] reviewer kit.

armanfatemi/nullius · not measured

cli-code-skills

Production-ready Claude Code skills — audit code quality, forge design docs, generate documentation, automate infrastructure.

Destynova2/cli-code-skills · not measured

cejel

Offline, deterministic engineering-trust certificate for a repository: tests, secrets, isolation, claim-vs-reality and CI discipline, scored against a published rubric with cited evidence. No network calls, no telemetry, no model call; the MCP server writes no files.

BargLabs/cejel · not measured

ai-debt-audit

Catches the garbage your AI assistant left behind — security shortcuts, secrets buried in git history, code nobody understands. One 0-100 score, 100% local, no LLM in the loop.

aniruddhavasudev/ai-debt-audit · not measured

aigon

aigon. Aigon is a local, open-source, spec-first software-delivery orchestrator for coding agents. It takes a Git-backed feature spec through isolated implementation, cross-agent review, and merge—using the agents and subscriptions you already have.

jayvee/aigon · not measured