saferskills: Instructions file for Claude Code

CLAUDE.md

saferskills CLAUDE.md is an instructions file for Claude Code from OpenLatch/saferskills. It costs 2,592 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for SaferSkills, a service that scans AI skills, MCP servers, hooks, and plugins and publishes trust reports. Its documentation covers the backend, frontend, code generation, uploads, and command-line checks.

In plain words
What is it for?
Use it when modifying SaferSkills ingestion, deterministic scans, upload flows, public reports, the Astro site, the FastAPI service, or its CLI.
Why use it?
It gives coding agents the project's rules and architecture so changes fit the existing scanning and reporting system.

Instructions file for Claude Code

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

This is OpenLatch/saferskills's own configuration. It tells Claude Code how to work on saferskills 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 saferskills configures →

Reuse

Borrowing it

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

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 saferskills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/openlatch/saferskills/claude-md.svg)](https://agentmods.dev/instructions/openlatch/saferskills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/openlatch/saferskills/claude-md"><img src="https://agentmods.dev/badge/instructions/openlatch/saferskills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,592 This file is loaded in full into every session.
When invoked 2,592 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02592 $0.02592
Opus 5 $0.01296 $0.01296
Sonnet 5 $0.00518 $0.00518
Haiku 4.5 $0.00259 $0.00259

Measured 8d ago against content hash ab63af051a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

saferskills 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 8d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — SaferSkills

SaferSkills is "every AI capability, independently scanned" — a public, free, Apache-2.0 trust-scoring service for skills, MCP servers, hooks, and plugins across every agent platform (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex CLI, Gemini CLI, Cline, OpenClaw). Anyone submits a GitHub URL → 30-second deterministic scan → public Yuka-style report with full rule trace, vendor right-of-reply, and a permalink.

Architecture: catalog ingestion (services/api/app/ingestion/) → scan engine (services/api/app/scan/ + detector rules under rubric/) → public report surface (webapp/ Astro SSG, indexed by saferskills.ai/items/<slug>) → CLI gate (cli/ npx). The codegen pipeline, FastAPI service, Astro public site, and design-system tokens all sit on top of this spine.

Submission front-ends: artifacts reach the same deterministic engine two ways — POST /api/v1/scans (GitHub URL) or direct upload POST /api/v1/scans/upload (one file / one .zip / N loose files, ≤10 MiB; visibility public|unlisted), surfaced as a single inline DropZone (webapp/src/lib/hooks/useUploadFlow.ts) usable from any page. Unlisted runs are reached only by an unguessable share_token (/api/v1/scans/r/{token} view/delete/promote/download); every public catalog query hard-filters visibility='public'. The full storage / visibility / shadow-row / multi-file-fan-out / report-routing contract lives in .claude/rules/database.md § Upload + visibility + frontend-patterns.md § Routing.

Stewardship: SaferSkills is an OpenLatch project, brand-independent. Footer attribution only — never cross-recommend OpenLatch from a SaferSkills surface. See .claude/rules/design-system.md § Anti-recommendation.


Quick Start

docker compose up                       # postgres + api + webapp (default)

Local dev (no Docker):

# Backend
cd services/api && uv sync && uv run uvicorn app.main:app --reload

# Frontend
cd webapp && pnpm install && pnpm dev

# Codegen
pnpm run generate                       # runs all 9 generators

Read the full file on GitHub · 147 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. 8d ago First seen · 147 lines · 2,592 tokens per session scan A ab63af051a07

Subscribe to this mod's changes

saferskills CLAUDE.md is an instructions file published in the GitHub repository OpenLatch/saferskills (7 stars, last pushed today), licensed Apache-2.0. It adds 2,592 tokens to every session, about $0.0130 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens