argot-suggest-rules

argot-suggest-rules is a skill for Claude Code, Codex from get-tmonier/argot. It costs 173 tokens per session (2,497 once invoked), scanned A, original, MIT.

A helper for turning coding conventions discovered by Argot into scripted custom rules. Argot is a code-analysis tool that learns where code and internal APIs usually appear in a repository.

In plain words
What is it for?
Use it to create rules such as keeping validation in schema files, database access in migrations, or business logic in a service layer.
Why use it?
It turns a useful observed convention into a reusable rule while keeping the developer responsible for deciding whether the rule is valid.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the argot plugin — 7 skills, 1 hook, 1 MCP server shipped together

Good fit Use it to create rules such as keeping validation in schema files, database access in migrations, or business logic in a service layer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/get-tmonier/argot/argot-suggest-rules
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.

Any agent
npx skills add get-tmonier/argot --skill argot-suggest-rules
Clone the repo
git clone --depth 1 https://github.com/get-tmonier/argot

Made for: Claude Code, Codex.

Or install argot, the plugin that ships this one along with the rest of its 7 skills, 1 hook, 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 argot-suggest-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/get-tmonier/argot/argot-suggest-rules/github.svg)](https://agentmods.dev/skills/get-tmonier/argot/argot-suggest-rules)
Your own site
<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-suggest-rules"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-suggest-rules/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.

agentmods 80×15 button for argot-suggest-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-suggest-rules"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-suggest-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00173 $0.02497
Opus 5 $0.00086 $0.01248
Sonnet 5 $0.00035 $0.00499
Haiku 4.5 $0.00017 $0.00250

Measured 10d ago against content hash baa6350843a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

argot-suggest-rules 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.

skills/argot-suggest-rules/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

argot-suggest-rules

argot-write-rule starts from a convention you state. This skill starts from what argot already found in the repo. argot conventions mines two kinds:

  • placement conventionswhere a kind of code lives: a feature (a call, an import) that concentrates in one location (a directory, a filename role, an extension) and is near-absent elsewhere. "validation lives in schema files", "queryInterface only in migrations", "business logic in the service layer, not in views". These are the team's structural rules.
  • vocabulary — the repo's own most-used internal API (shared helpers, the objects everyone routes through).

The mining is corpus- and framework-agnostic (pure feature×location association) and every candidate carries its evidence. You turn a chosen one into a real scripted rule — same manifest + Rhai + fixture-gate shape as argot-write-rule, same custom group. Full reference: https://argot.tmonier.com/docs/custom-rules/.

This is a deliberate later workflow after audit and ordinary check activation; it does not make a discovered convention a default CI or commit gate. It is assisted authoring, not rule generation or lifecycle wiring: a user still chooses the convention, reviews the rule, and configures any workflow that runs it.

Preconditions

  1. argot --version — if missing, tell the user how to install it (https://argot.tmonier.com/docs/getting-started/) and stop.
  2. argot conventions needs a complete, committed, fresh fit snapshot. Run argot status --format json; if snapshot.complete or snapshot.committed is false, stop and finish argot-setup first. If the config is out of sync or refresh is recommended, hand off to argot-refresh on the accepted branch; it reviews scope and mutes before the local fit and committed .argot/ update. Do not fit implicitly: mixing fitted vocabulary with a newer live placement catalog would codify an incoherent convention.

Read the full file on GitHub · 199 lines

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. 10d ago First seen · 199 lines · 173 tokens per session scan A baa6350843a9

Subscribe to this mod's changes

argot-suggest-rules is a skill published in the GitHub repository get-tmonier/argot (48 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 2,497 once invoked, about $0.0009 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

boundary-validation

This skill should be used when the user asks to "validate input", "parse request data", "handle form data", "add Zod schema", "sanitize user input", or creates API endpoints and system boundaries. Provides parse-don't-validate patterns with schema validation for type-safe boundary enforcement and hostile input defense.

dean0x/devflow · 67 tokens

consistency

This skill should be used when reviewing code for naming convention violations, pattern deviations, or inconsistent API styles.

dean0x/devflow · 24 tokens

documentation

This skill should be used when reviewing for documentation drift, missing API docs, or stale comments.

dean0x/devflow · 21 tokens

java

This skill should be used when the user works with Java files (.java), asks about "records", "sealed classes", "Optional", "streams", "composition over inheritance", or discusses modern Java patterns and API design. Provides patterns for type system usage, error handling, immutability, and concurrency.

dean0x/devflow · 63 tokens

patterns

This skill should be used when the user asks to "create an API endpoint", "add CRUD operations", "implement event handlers", "set up logging", "add configuration", or builds features involving database operations, REST/GraphQL APIs, pub/sub patterns, or service configuration. Provides implementation patterns that…

dean0x/devflow · 68 tokens

typescript

This skill should be used when the user works with TypeScript files (.ts/.tsx), asks about "generics", "type guards", "utility types", "strict typing", "discriminated unions", or discusses type safety and inference. Provides patterns for Result types, exhaustive checks, branded types, and type-safe API contracts.

dean0x/devflow · 69 tokens