What is agentic-skills CLAUDE.md?

A set of instructions for working on a public library of Claude and Cursor skills. Each skill is a folder containing Markdown instructions that describe how an agent should behave.

Use it when authoring or refining skills in the vidhunnan/agentic-skills repository, especially their SKILL.md files and registration details.

It gives contributors the repository's structure and rules for adding or changing skills. It explains how skill names, folders, and triggering descriptions must match.

How vidhunnan/agentic-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vidhunnan/agentic-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/vidhunnan/agentic-skills/prod-stable/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vidhunnan/agentic-skills

Made for: Claude Code.

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/vidhunnan/agentic-skills/claude-md/github.svg)](https://agentmods.dev/instructions/vidhunnan/agentic-skills/claude-md)

Your own site

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

Per session 3,535 This file is loaded in full into every session.

When invoked 3,535 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	$0.03535	$0.03535
Opus 5.5	$0.01414	$0.01414
Sonnet 5.5	$0.00707	$0.00707
Haiku 4.5	$0.00353	$0.00353

Measured 2mo ago against content hash f2ba4df2149b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-skills CLAUDE.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.

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A personal library of Claude / Cursor-compatible agent skills. Each skill is a self-contained folder of Markdown (a SKILL.md plus optional supporting docs) — there is no build system, no test runner, and no application code. "Working on the code" here means authoring and refining skill definitions and their specs.

Public, and forkable. Treat everything here as published: it ships to the plugin marketplace and is documented at https://agentic-skills.vidhunnan.design.

Layout & conventions

One folder per skill under skills/, kebab-case, where the folder name must match the name field in that skill's SKILL.md frontmatter.
Each skill's entry point is skills/<name>/SKILL.md. Its frontmatter (name, description, allowed-tools, disable-model-invocation, plus optionally argument-hint) is the contract that drives how and when the skill triggers — the description doubles as the auto-trigger matcher, so it must enumerate the natural-language phrases and the /<name> slash form that should fire it.
Skill folder = plugin. Each skills/<name>/ doubles as an installable plugin by carrying its own .claude-plugin/plugin.json next to SKILL.md. This is the reusable pattern for every future skill: it keeps the "one folder per skill under skills/" convention and the standalone-copy install (cp -r skills/<name> ~/.claude/skills/) working, with no separate plugins/ tree.
PRDs for non-trivial skills live in docs/prds/<name>.md. When a SKILL.md is still a stub, the PRD is the source of truth for the output template, trigger rules, and per-surface behavior — read it before implementing. Keep the PRD in sync when the skill's scope changes.
The repo-root .claude-plugin/marketplace.json lists every skill as a plugin, each source pointing at its skills/<name> folder. Add an entry here whenever you add a skill.
Nothing referencing internal/employer-specific systems or unreleased work belongs in this repo (it's headed for public release).

Read the full file on GitHub · 145 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 · 145 lines · 3,535 tokens per session scan A f2ba4df2149b

Subscribe to this mod's changes

agentic-skills CLAUDE.md is an instructions file published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 3,535 tokens to every session, about $0.0141 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

agentic-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentic-skills CLAUDE.mdvidhunnan/agentic-skills	Instructions file	2	2mo ago	MIT	A	3,535	Claude Code
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	5,516	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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

agentic-skills: Instructions file for Claude Code