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.
npx agentmods add instructions/fvadicamo/dev-agent-skills/claude-mdgit clone --depth 1 https://github.com/fvadicamo/dev-agent-skillsWrote 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.
[](https://agentmods.dev/instructions/fvadicamo/dev-agent-skills/claude-md)<a href="https://agentmods.dev/instructions/fvadicamo/dev-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/fvadicamo/dev-agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02701 | $0.02701 |
| Opus 5 | $0.01350 | $0.01350 |
| Sonnet 5 | $0.00540 | $0.00540 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
dev-agent-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 200 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.
Project overview
A collection of Claude Code agent skills and hooks for development workflows, distributed as a plugin marketplace. Contains 7 skills and 1 hook organized into 5 plugins:
- github-workflow plugin:
git-commit,github-pr-creation,github-pr-merge,github-pr-review - skill-authoring plugin:
creating-skills - guardrails plugin:
guard-destructivePreToolUse hook - privacy-guard plugin:
privacy-guardskill (session rules + pre-commit denylist gate for public repos) - decision-records plugin:
decision-recordsskill (writes ADRs, and validates a collection against the convention it already follows)
Skills are model-invoked (Claude activates them based on user intent, not slash commands). The hook runs automatically on every Bash tool call.
Architecture
.claude-plugin/
marketplace.json # Marketplace registry: lists all plugins
plugins/
<plugin-name>/
.claude-plugin/
plugin.json # Plugin manifest
skills/ # Skills (skill plugins) - auto-discovered
<skill-name>/
SKILL.md # Main skill file (YAML frontmatter + markdown body)
references/ # Optional deep-dive docs loaded on demand
scripts/ # Optional executables the skill runs in place
hooks/ # Hooks (guardrails plugin) - auto-discovered
hooks.json # Hook registration
guard-destructive.sh # Hook script, run via ${CLAUDE_PLUGIN_ROOT}
tests/ # regression suite - three plugins have one
run.sh # guardrails: cases/*.txt table; the other two: inline
cases/*.txt # (guardrails only)
Key file: marketplace.json
Lists the plugins. Each plugin is a self-contained directory under plugins/, referenced only by source (e.g. ./plugins/github-workflow); its components are auto-discovered from that directory. The marketplace entry carries no skills/hooks arrays - this is the standard Claude Code plugin layout. To add a plugin, create plugins/<name>/ with a .claude-plugin/plugin.json and its components, then add an entry here.
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.
- 5d ago First seen · 200 lines · 2,701 tokens per session scan A 96f08663e5fc
dev-agent-skills CLAUDE.md is an instructions file published in the GitHub repository fvadicamo/dev-agent-skills (72 stars, last pushed 8d ago), licensed MIT. It adds 2,701 tokens to every session, about $0.0135 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
repo-kit CLAUDE.md
Claude Code instructions for PBNZ/repo-kit, a project described as: RepoKit — a reusable repo standard + /new-repo scaffolder, packaged as a Claude Code plugin.
qa-orchestra CLAUDE.md
Claude Code instructions for Anasss/qa-orchestra, covering qa orchestra — claude code instructions, what this project is, quick start, 1. clone into your workspace and 2. fill in your project context.
the-foundry AGENTS.md
AGENTS.md instructions for attac-t/the-foundry, covering the foundry, doctrine and rules.
swarms CLAUDE.md
Instructions for DheerG/swarms, a project described as: Achieve extraordinary results with claude code across a variety of tasks.