Borrowing it
Nothing to install: this file belongs to swarmclawai/agent-skills-lint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swarmclawai/agent-skills-lint/main/AGENTS.mdgit clone --depth 1 https://github.com/swarmclawai/agent-skills-lintWrote 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/instructions/swarmclawai/agent-skills-lint/agents-md)<a href="https://agentmods.dev/instructions/swarmclawai/agent-skills-lint/agents-md"><img src="https://agentmods.dev/badge/instructions/swarmclawai/agent-skills-lint/agents-md/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.
<a href="https://agentmods.dev/instructions/swarmclawai/agent-skills-lint/agents-md"><img src="https://agentmods.dev/badge/instructions/swarmclawai/agent-skills-lint/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01294 | $0.01294 |
| Opus 5 | $0.00647 | $0.00647 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
agent-skills-lint 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-skills-lint — agent-facing reference
This document is the machine-friendly spec for driving agent-skills-lint programmatically from a coding agent (Claude Code, Codex, Cursor, Cline, Aider, Copilot, etc.).
Tip: You don't need to parse this file. Run agent-skills-lint help-agents --json (or any other command with --json) and the CLI will emit the full catalog in one line of JSON.
Global flags
| Flag | Type | Effect |
|---|---|---|
--json |
boolean | Print a one-line JSON envelope on stdout |
--quiet |
boolean | Suppress stderr logs |
--verbose |
boolean | Verbose logs on stderr |
--cwd <path> |
path | Override the working directory for relative paths |
--flavor <id> |
enum | One of: claude, codex, opencode, aider, copilot, gemini, cursor, claw, droid, trae, trae-cn, hermes, kiro, antigravity, generic |
JSON envelope
Every command emits exactly one line of JSON on stdout when --json is passed.
{"ok": true, "data": {...}}
On failure:
{"ok": false, "error": {"code": "E_VALIDATION", "message": "...", "hint": "..."}}
Stable error codes:
E_VALIDATION— bad flag, bad input, missing required argE_INTERNAL— uncaught exception (please file an issue)
Exit codes
0— success1— user error (validation failed, lint errors found, collisions found)2— internal error
Commands
lint <path>
Validate a single skill file or a whole directory.
{
"ok": true,
"data": {
"flavor": "claude",
"skillCount": 12,
"errorCount": 0,
"warningCount": 3,
"issues": [
{
"path": "...",
"rule": "filename-mismatch",
"severity": "warning",
"message": "...",
"hint": "..."
}
]
}
}
Rules:
| Rule | Severity | When |
|---|---|---|
load/io |
error | File can't be read |
load/parse |
error | Frontmatter is not parseable YAML |
load/schema |
error | Frontmatter fails the flavor's schema (missing name, bad description, etc.) |
description-too-short |
warning | Description < 20 chars |
description-too-long |
warning (error with --strict) |
Description > 500 chars |
filename-mismatch |
warning | Basename doesn't equal <name>.<ext> or SKILL.md |
unknown-frontmatter-key |
warning (error with --strict) |
Key not in the flavor's known set |
empty-body |
warning | Skill body is empty |
name-collision |
error | Two or more skills share a name |
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.
- 9d ago First seen · 165 lines · 1,294 tokens per session scan A eb68932b4731
agent-skills-lint AGENTS.md is an instructions file published in the GitHub repository swarmclawai/agent-skills-lint (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,294 tokens to every session, about $0.0065 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.