What is claude-skills AGENTS.md?

Project-specific instructions for shaharsha/claude-skills, a collection of reusable agent skills. They explain how each skill's files, names, descriptions, scripts, and documentation must be maintained.

Creating or renaming skills, maintaining their metadata and scripts, and updating marketplace and human-readable documentation.

They reduce the risk of adding or renaming a skill without updating the files that make it installable and discoverable.

How shaharsha/claude-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to shaharsha/claude-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/shaharsha/claude-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/shaharsha/claude-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/shaharsha/claude-skills/agents-md/github.svg)](https://agentmods.dev/instructions/shaharsha/claude-skills/agents-md)

Your own site

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

Per session 821 This file is loaded in full into every session.

When invoked 821 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	$0.00821	$0.00821
Opus 5.5	$0.00328	$0.00328
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash 578afe105427, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-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 2mo 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-skills

Personal Agent Skills library, published as the shaharsha-skills marketplace. Each skill is a folder under skills/<name>/ with a SKILL.md. Skills are consumed by Claude Code, Codex, Cursor, and other Agent-Skills harnesses — keep them harness-agnostic (no assumptions about a specific host's tools).

Edit skills here, in this repo. Each is symlinked into ~/.claude/skills/<name>, so that path is this repo — don't expect a separate editable copy under ~/.claude/skills.

Adding or renaming a skill — update ALL of these

Miss one and the skill ships half-wired (installs but isn't listed, or is listed but 404s):

skills/<name>/SKILL.md — frontmatter name + description. The description is when to trigger (third-person "Use when…", keyword-rich); it's the only thing that makes the skill fire, so it is not a workflow summary.
skills/<name>/README.md — the GitHub landing page for that folder. SKILL.md is for the model; README.md is for the human — it links into SKILL.md and reference/ rather than restating procedure. Sections: pitch, why it exists, what it does, install (marketplace + monorepo path), requirements, quick start, gotchas, related skills, license. Copy the shape from any existing one.
.claude-plugin/marketplace.json — add ./skills/<name> to the main shaharsha-skills plugin (and update its "All N skills" count in that plugin's description) and to the fitting category plugin; bump metadata.version.
README.md — the matching /plugin install <category>@shaharsha-skills comment line, plus a one-line row in that category's table. One sentence, not a paragraph — the long description lives in the skill's own README.
~/Projects/shahar-sh/public/skills.html — separate repo. Add a skill card, append the name to the <meta name="description"> list, and bump the two "N skills" counts. Pushing main there auto-deploys to Cloudflare Pages (gh run watch to confirm).
ln -s "$PWD/skills/<name>" ~/.claude/skills/<name> — the symlink that makes it loadable locally.

Read the full file on GitHub · 33 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.

2mo ago First seen · 33 lines · 821 tokens per session scan A 578afe105427

Subscribe to this mod's changes

claude-skills AGENTS.md is an instructions file published in the GitHub repository shaharsha/claude-skills (6 stars, last pushed today), licensed MIT. It adds 821 tokens to every session, about $0.0033 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.

Building agents

claude-skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-skills AGENTS.mdshaharsha/claude-skills	Instructions file	6	today	MIT	A	821	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-skills: Instructions file for Claude Code