agentmods.dev

mKit CLAUDE.md

A repository instruction file that sets rules for using Claude Code and other AI assistants, including saving prompts and session logs.

In plain words
What is it for?
Use it to guide AI-assisted pull requests, create prompt and session files, and enforce the project’s AI governance process.
Why use it?
It makes AI-assisted work traceable by requiring specific artifacts in the repository and references to them in pull requests.

Instructions file

1 1mo ago A scan 362 tokens original MIT
View the source file jscraik/mKit
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/jscraik/mkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/jscraik/mKit
Per session 362 This file is loaded in full into every session.
When invoked 362 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00362 $0.00362
Opus 5 $0.00181 $0.00181
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 2d ago against content hash 36a3767d00f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mKit 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 2d 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 · 45 lines

What it actually says

Claude AI Governance

This repository contains governance rules for Claude Code and other AI assistants working in this codebase.

AI Assistance Governance (Model A)

This project follows Model A AI artifact governance: prompts and session logs are committed artifacts in the repository.

When creating PRs with AI assistance

Claude must:

  1. Save artifacts to ai/ directory:

    • Final prompt → ai/prompts/YYYY-MM-DD-<slug>.yaml
    • Session summary → ai/sessions/YYYY-MM-DD-<slug>.json

  2. Commit both files in the PR branch:

    git add ai/prompts/YYYY-MM-DD-<slug>.yaml ai/sessions/YYYY-MM-DD-<slug>.json

  3. Reference exact paths in PR body:

    • Under AI assistance section:
      • Prompt: ai/prompts/YYYY-MM-DD-<slug>.yaml
      • Session: ai/sessions/YYYY-MM-DD-<slug>.json
    • In AI Session Log details:
      • Log file: ai/sessions/YYYY-MM-DD-<slug>.json
      • Prompt file: ai/prompts/YYYY-MM-DD-<slug>.yaml

  4. Do NOT:

    • Embed prompt/log excerpts in the PR body
    • Link to external logs or pastebins
    • Skip creating artifacts when AI assistance is acknowledged

  5. Abort if artifacts cannot be created and committed.

Artifact Templates

See ai/prompts/.template.yaml and ai/sessions/.template.json for required fields.

PR Template

All PRs must use .github/PULL_REQUEST_TEMPLATE.md which includes required AI disclosure sections.

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. 2d ago First seen · 45 lines · 362 tokens per session scan A 36a3767d00f0

Subscribe to this mod's changes

mKit CLAUDE.md is an instructions file published in the GitHub repository jscraik/mKit (1 stars, last pushed 1mo ago), licensed MIT. It adds 362 tokens to every session, about $0.0018 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.

boilerplatecloudflaremcp
Related

Other instructions, from other repositories

svelteflare AGENTS.md

Instructions for pinebasedev/svelteflare, covering agent rules for this project, theme fidelity (non-negotiable), talking to the user and deep-dive skills.

pinebasedev/svelteflare · 874 tokens

svelteflare CLAUDE.md

Instructions for pinebasedev/svelteflare, a project described as: A SvelteKit, Hono and Cloudflare SaaS boilerplate to launch your next MVP.

pinebasedev/svelteflare · 5 tokens

ant-design-pro CLAUDE.md

Claude Code instructions for ant-design/ant-design-pro, covering claude.md, project, commands, critical rules and architecture essentials.

ant-design/ant-design-pro · 1,528 tokens

agents AGENTS.md

AGENTS.md instructions for cloudflare/agents, covering agents.md, project overview, repository structure, nested agents.md files and setup.

cloudflare/agents · 2,131 tokens

scrapai-cli CLAUDE.md

Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.

discourselab/scrapai-cli · 8,964 tokens

zentinel AGENTS.md

Instructions for zentinelproxy/zentinel, covering zentinel, philosophy (north star), architecture, crates and core crates.

zentinelproxy/zentinel · 2,253 tokens