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/nacif-software/skills/claude-mdgit clone --depth 1 https://github.com/nacif-software/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/nacif-software/skills/claude-md)<a href="https://agentmods.dev/instructions/nacif-software/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/nacif-software/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 | $0.01098 | $0.01098 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
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 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.
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 — 52 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
Nacif Skills is a collection of agent skills — each skill is a folder under skills/ with a SKILL.md (frontmatter + prose) plus optional references/, scripts/, and assets/. Skills are distributed straight from GitHub via npx skills and as a Claude Code plugin marketplace (.claude-plugin/marketplace.json).
The primary deliverable is the content of each SKILL.md and its supporting docs. Check README.md and CONTRIBUTING.md for the current install/distribution story, and docs/ for the suite model.
Where the authoritative guidance lives
CONTRIBUTING.md— how to scaffold, write, name, and test a skill; the requiredSKILL.mdsections.docs/architecture.md— the suite model: skill types, the default workflow graph, and how skills relate.docs/subagents.md— delegation and context rules.docs/workflows/<workflow>.md— per-workflow behavior and artifact contracts.docs/decisions/— numbered ADRs; read the relevant one before changing suite-level behavior.skills/example-skill/— the annotated template to copy when starting a new skill.
Validating a skill
Skills are prose contracts rather than compiled code, so validation is behavioral:
claude plugin validate . # validate the marketplace manifest
npx skills add ./skills/<skill-name> # install one skill into a test project and dogfood it
To confirm a skill works, install it and give an agent a task that should trigger it — verify it activates and produces the promised artifact. Match whatever build/lint/test tooling exists at the time by inspecting the repo (package manifests, CI config, docs/) rather than assuming.
The two skill types
Every skill is either:
- Workflow skill — owns an end-to-end user journey with user-facing gates and durable artifacts (e.g.
design-feature,plan-implementation,execute-plan,review-pr). It decides the next phase and asks the user to choose. - Discipline skill — enforces one reusable habit used inside workflows; stays small and never owns the full journey (e.g.
context-briefing,task-dispatch-loop,verification-gate).
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.
- 4d ago First seen · 52 lines · 1,098 tokens per session scan A 3c970ff0beb2
skills CLAUDE.md is an instructions file published in the GitHub repository nacif-software/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,098 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.