skill-issue CLAUDE.md

skill-issue CLAUDE.md is an instructions file for coding agents from paultyng/skill-issue. It costs 446 tokens per session, scanned B, original, MIT.

Repository instructions for a personal collection of Claude Code skills, rules, scripts, and settings. They explain how the files are organized and synchronized into the user's Claude configuration.

In plain words
What is it for?
They guide the creation and maintenance of skills, rules, scripts, settings, and the installation workflow for this repository.
Why use it?
They prevent changes from being made in the wrong location or in a way that is lost during synchronization.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/paultyng/skill-issue/claude-md
Clone the repo
git clone --depth 1 https://github.com/paultyng/skill-issue

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 skill-issue CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paultyng/skill-issue/claude-md.svg)](https://agentmods.dev/instructions/paultyng/skill-issue/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paultyng/skill-issue/claude-md"><img src="https://agentmods.dev/badge/instructions/paultyng/skill-issue/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 446 This file is loaded in full into every session.
When invoked 446 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.00446 $0.00446
Opus 5 $0.00223 $0.00223
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00045 $0.00045

Measured 4d ago against content hash 7108a9a6f82a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

skill-issue CLAUDE.md scanned grade B 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `settings.merge.json` — Curated keys merged into `~/.claude/settings.json` (model, permissions, hooks, plugins).
CLAUDE.md · 35 lines

What it actually says

CLAUDE.md

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

What This Repo Is

Personal user-level Claude Code skills, rules, and settings. The canonical clone (this repo) is the source of truth; ~/.claude/ is populated by ./install.sh.

Repository Structure

  • skills/ — Multi-step agent workflows (SKILL.md per directory). See .claude/rules/skill-authoring.md for conventions.
  • rules/ — Behavioral rules that auto-load every session. See .claude/rules/rule-authoring.md for conventions.
  • scripts/ — Shell scripts including statusline.
  • settings.merge.json — Curated keys merged into ~/.claude/settings.json (model, permissions, hooks, plugins).
  • install.sh — Install/sync script.

Creating Skills and Rules

Use /create-skill and /create-rule respectively. Do not author SKILL.md or rule files from scratch.

Sync workflow

  • ~/.claude/ is populated by ./install.sh running from this canonical clone.
  • Edits to skills/, rules/, scripts/, and top-level files in this repo flow into ~/.claude/ on each install.
  • Personal/local skills/rules/scripts in ~/.claude/ are preserved (never deleted).
  • settings.json is jq-merged: specific keys (model, effortLevel, statusLine, enabledPlugins, extraKnownMarketplaces, permissions.allow, hooks) flow from settings.merge.json; everything else stays user-local.

Portability

This repo must remain portable and free of company-specific content:

  • No internal URLs, proprietary tool names, or org-specific workflows in skills, rules, or settings.
  • Skills that need org-specific context should read it from project-level CLAUDE.md, REVIEW.md, or .claude/rules/ at runtime.
  • MCP tool references use fully qualified names (ServerName:tool_name).
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. 4d ago First seen · 35 lines · 446 tokens per session scan B 7108a9a6f82a

Subscribe to this mod's changes

skill-issue CLAUDE.md is an instructions file published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 23d ago), licensed MIT. It adds 446 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.