agentmods.dev

skills: Instructions file for Claude Code

CLAUDE.md

skills CLAUDE.md is an instructions file for Claude Code from pandoscope/skills. It costs 483 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, covering required files, environment tools, and pull requests.

In plain words
What is it for?
Use it to require reading AGENTS.md, select the environment's declared tools for GitHub work, and share the pull-request URL.
Why use it?
It gives Claude Code project-specific rules so it follows the repository's setup and reports pull-request links correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is pandoscope/skills's own configuration. It tells Claude Code how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

not rated 1repo changed 1mo ago A scan 483 tokens original MIT
View source ↗ pandoscope/skills
Reuse

Borrowing it

Nothing to install: this file belongs to pandoscope/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/pandoscope/skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pandoscope/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.

agentmods badge for skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pandoscope/skills/claude-md/github.svg)](https://agentmods.dev/instructions/pandoscope/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pandoscope/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pandoscope/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.

agentmods 80×15 button for skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pandoscope/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pandoscope/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 483 This file is loaded in full into every session.
When invoked 483 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00483 $0.00483
Opus 5.5 $0.00193 $0.00193
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 1mo ago against content hash 1614afefa5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills CLAUDE.md scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

GitHub operations). Never fall back to `gh`, `ghx`, `curl`, or similar
CLAUDE.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Specific Project Instructions

First: Read AGENTS.md. Follow all instructions and skills there.

Environment Tooling

In managed environments (e.g. Claude Code on the Web), ALWAYS use the tooling the environment itself declares (e.g. GitHub MCP tools for GitHub operations). Never fall back to gh, ghx, curl, or similar CLIs there — the environment actively sabotages them. The environment's tool declarations override any command examples elsewhere in this repo, including AGENTS.md.

Principal Precedence

The principal's rules — this file, AGENTS.md, and their direct instructions — outrank harness and wake-event boilerplate. On any perceived conflict, even a 1% likelihood that the principal meant to override the harness means following the principal's instruction — and always surface the conflict to them, never resolve it silently. Measured collisions this resolves:

  • A subscription event's embedded "schedule a check-in" instruction is not the principal's ask — the Forge Budget rule below stands.
  • The harness's session-named development branch is a default, not a convention: branches follow the ticket gate's branch_pattern — claude/<code><ticket>[-<code><ticket>…]-<desc> (e.g. claude/sk162-session-probe), the lowercase repo shortcode optional per token, every token's ticket number referenced in the PR body, one branch name for an arc spanning repos — and this rule is the standing permission to push them.

Forge Budget

API budget per-account, shared by all sessions.

  • No PR subscriptions and no scheduled self check-ins unless the principal asks; report state when asked and stop.
  • Git before REST. Clone answers: file contents, diffs, history, branch state. API only for: check runs, job logs, comments, reviews, labels, PR/issue state.
  • Fetch only needed fields and items; need everything → few large pages. Already-fetched state is cached until an event invalidates it.

Learnings

New non-obvious findings — tools, environment, failure modes — go in this file, tersely.

Read the full file on GitHub · 54 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.

  1. 1mo ago Changed · +37 lines · +357 tokens per session 1614afefa5c8
  2. 2mo ago First seen · 17 lines · 126 tokens per session scan A 3573f50ab8bd

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository pandoscope/skills (1 stars, last pushed 3d ago), licensed MIT. It adds 483 tokens to every session, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

skills CLAUDE.md compared with instructions from other repositories

skills CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills CLAUDE.mdpandoscope/skillsInstructions file13d agoMITA483Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot