What is skills AGENTS.md?

Repository instructions for a marketplace of reusable coding-agent skills and plugins, including where skills, evaluations, and distribution manifests belong.

Use them when adding or modifying plugins, skills, manifests, repository evaluations, or installation links in the marketplace.

They keep skills discoverable and consistent across supported agent tools while preventing duplicate sources and misplaced evaluation files.

How bitwise-media-group/skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to bitwise-media-group/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bitwise-media-group/skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bitwise-media-group/skills

Made for: Claude Code, 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/bitwise-media-group/skills/agents-md/github.svg)](https://agentmods.dev/instructions/bitwise-media-group/skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bitwise-media-group/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/bitwise-media-group/skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bitwise-media-group/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/bitwise-media-group/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,069 This file is loaded in full into every session.

When invoked 2,069 The same file — it is already loaded in full.

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.

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 5.1	$0.02069	$0.02069
Opus 5.5	$0.00828	$0.00828
Sonnet 5.5	$0.00414	$0.00414
Haiku 4.5	$0.00207	$0.00207

Measured 9d ago against content hash 51e8856d88e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills 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.

AGENTS.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bitwise skills — repository conventions

This repo is the bitwise skills/plugin marketplace: agent skills packaged as plugins, consumable by Claude Code, OpenAI Codex CLI, Google Antigravity, and OpenCode. The global ~/.claude/CLAUDE.md (Conventional Commits, commit.sh signing handoff) applies on top of this file.

CLAUDE.md is a symlink to this file — always edit AGENTS.md, never CLAUDE.md.

Layout

One plugin per directory under plugins/<plugin>/. Skills are the canonical source of truth at plugins/<plugin>/skills/<skill-name>/SKILL.md — they exist exactly once; every distribution channel (Claude/Codex marketplaces, install.sh symlinks) points at this tree.
Evals live at plugins/<plugin>/evals/<skill-name>/ (triggers.json, evals.json, fixtures, and the committed results.json the sweeps write), not inside the skill directory, so installed skills stay lean.
Skill directory name must equal the frontmatter name.
Skill names are globally namespaced by prefix (e.g. terraform-style, not style) because Codex/Antigravity/OpenCode install skills into flat shared directories.
The docs site (see Docs site): zensical.toml, pyproject.toml + uv.lock, hand-written pages in docs/ (index.md, install.md, contributing.md), theme in overrides/ + docs/stylesheets/extra.css, and the generator scripts/gen-docs.py.

Dual manifests (Claude + Codex)

Every plugin carries two manifests; the repo carries two marketplace manifests:

Consumer	Marketplace (repo root)	Plugin manifest
Claude Code	`.claude-plugin/marketplace.json`	`plugins/<n>/.claude-plugin/plugin.json`
Codex CLI	`.agents/plugins/marketplace.json`	`plugins/<n>/.codex-plugin/plugin.json`

Rules:

Versions stay in sync between the two plugin manifests (enforced by evolve run checks). Codex requires strict semver.
Marketplace source paths are explicit and ./-prefixed ("./plugins/terraform"). Do not use Claude's metadata.pluginRoot — Codex fallback-reads Claude's manifest and resolves sources against the repo root.
Never add a hooks/ directory to a plugin. Codex default-discovers hooks/hooks.json with an incompatible schema.

Read the full file on GitHub · 125 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.

9d ago Changed · +28 lines · +583 tokens per session 51e8856d88e1
1mo ago Changed · -1 lines · -9 tokens per session 11723f60cacc
2mo ago First seen · 98 lines · 1,495 tokens per session scan A 1907d2aaed3b

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository bitwise-media-group/skills (3 stars, last pushed yesterday), licensed MIT. It adds 2,069 tokens to every session, about $0.0083 per session on Opus 5.5. 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.

agent-skills claude-code-marketplace claude-code-skills codex-skills cursor-skills gemini-skills

skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills AGENTS.mdbitwise-media-group/skills	Instructions file	3	yesterday	MIT	A	2,069	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

skills: Instructions file for Claude Code