What is claude-code-gauntlet AGENTS.md?

A set of repository instructions for Claude Code, an AI coding assistant, working on the claude-code-gauntlet plugin. It explains project rules, directory-specific guidance, scripts, and tests.

Use it when editing the plugin’s workflows, scripts, agents, or tests. It helps decide where changes belong and how to verify them.

It gives the assistant the project context and constraints needed to make changes that fit the repository. It also reduces errors such as adding npm files or ignoring local rules.

claude-code-gauntlet AGENTS.md — Instructions file for Codex and OpenCode by liatrio-labs: A set of repository instructions for Claude Code,

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 instructions/liatrio-labs/claude-code-gauntlet/agents-md

Clone the repo

git clone --depth 1 https://github.com/liatrio-labs/claude-code-gauntlet

Made for: Codex, OpenCode.

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/instructions/liatrio-labs/claude-code-gauntlet/agents-md.svg)](https://agentmods.dev/instructions/liatrio-labs/claude-code-gauntlet/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/liatrio-labs/claude-code-gauntlet/agents-md"><img src="https://agentmods.dev/badge/instructions/liatrio-labs/claude-code-gauntlet/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,263 This file is loaded in full into every session.

When invoked 2,263 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.02263	$0.02263
Opus 5	$0.01131	$0.01131
Sonnet 5	$0.00453	$0.00453
Haiku 4.5	$0.00226	$0.00226

Measured today against content hash fe87adb4502c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-gauntlet AGENTS.md 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 today.

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.

AGENTS.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

claude-code-gauntlet is a Claude Code marketplace plugin — no server, database, or Docker. "Running it" means running the test suites and the stdlib-only Python pipeline scripts.

Directory-scoped rules live in nested AGENTS.md files: workflows/, scripts/, agents/. Read the one for the directory you are editing.

Design

Build the mechanism, not the instruction. Whatever code, a schema, a data structure, or a removed capability can enforce, it must. Prose in an instruction, prompt, or agent file is the fallback for what cannot be made structural.

"Add more text" is a design smell. If that is the fix under consideration, the shape is wrong — change the shape.

Extending should cost one edit. A new dimension, field, or agent belongs in one place. If it takes coordinated edits across N files, fix the shape rather than documenting the ritual.

Tooling boundary (no npm in the tree)

No package.json, lockfile, or node_modules is tracked in the repository.
The shipped pipeline runtime (workflows/src, workflows/pipeline.js) has zero dependencies — language globals plus the host-injected agent/parallel/ pipeline/args only. No import survives into the bundle: build.js strips relative sibling imports and fails on any other specifier, which would ship as an undefined reference. See workflows/AGENTS.md for the sandbox surface.
Pinned static binaries in CI are permitted (e.g. Biome for the js-lint job). Bumps are manual and deliberate; do not add a package manifest to get Dependabot coverage for those pins.
This does not forbid npm on the CI runner (validate.yml already installs the Claude Code CLI globally).

Scripts

stdlib-only Python. No pip dependencies in shipped scripts/ runtime — nothing under scripts/ may import a non-stdlib module. Pinned CI tooling in pyproject.toml [dependency-groups] (pytest, pytest-cov, coverage) is exempt and never runs inside the plugin.
Language-agnostic. Scripts must not assume a language in the reviewed codebase. Use --exclude-dir for non-source directories, never --include=*.py-style filters.

Read the full file on GitHub · 168 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.

today Changed · +5 lines · +172 tokens per session fe87adb4502c
5d ago First seen · 163 lines · 2,091 tokens per session scan A f3a471c7a9c2

Subscribe to this mod's changes

claude-code-gauntlet AGENTS.md is an instructions file published in the GitHub repository liatrio-labs/claude-code-gauntlet (12 stars, last pushed today), licensed Apache-2.0. It adds 2,263 tokens to every session, about $0.0113 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.

Code review Testing adversarial claude-code claude-code-plugin github gitlab

agent-smith CLAUDE.md

Claude Code instructions for holgerleichsenring/agent-smith, covering agent-smith — ai agent instructions, context files (read in this order), phase directory structure, experiential memory (remember / recall) and minting a phase id.

holgerleichsenring/agent-smith · 2,302 tokens

nyann CLAUDE.md

Claude Code instructions for thettwe/nyann, covering claude.md, architecture & conventions, skill authoring rules (apply to every skill.md) and scope reminders.

thettwe/nyann · 559 tokens

oss-scout CLAUDE.md

Claude Code instructions for costajohnt/oss-scout, covering claude.md, project overview, architecture, key design decisions and file structure.

costajohnt/oss-scout · 1,875 tokens

claude-code-plugins CLAUDE.md

Instructions for zhebil/claude-code-plugins, covering claude.md, what this repo is, plugins, auto-enrich and common commands.

zhebil/claude-code-plugins · 1,954 tokens

pr-comments-resolver CLAUDE.md

Instructions for Dropelikeit/pr-comments-resolver, covering pr comments resolver — development guide, project structure, plugin format, conventions and adding a new skill.

Dropelikeit/pr-comments-resolver · 281 tokens

ship-it AGENTS.md

Instructions for khrichtchatyi/ship-it: Each rule or paragraph in a SKILL.md file must be a single sentence; use semicolons, colons, or em dashes to chain related clauses inside one sentence, but never start a second sentence inside the same paragraph — split it into a new paragraph instead.

khrichtchatyi/ship-it · 184 tokens