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/mohamedsaleh14/contextgit/claude-mdgit clone --depth 1 https://github.com/Mohamedsaleh14/ContextGitWrote 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/mohamedsaleh14/contextgit/claude-md)<a href="https://agentmods.dev/instructions/mohamedsaleh14/contextgit/claude-md"><img src="https://agentmods.dev/badge/instructions/mohamedsaleh14/contextgit/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 5.1 | $0.02280 | $0.02280 |
| Opus 5 | $0.01140 | $0.01140 |
| Sonnet 5 | $0.00456 | $0.00456 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
ContextGit 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 6d 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 — 226 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) and Cursor when working with code in this repository.
IMPORTANT: This Project Uses contextgit
This repository is managed with contextgit. Before making changes to requirements or documentation:
Automatic Workflow for AI Assistants
-
Before modifying requirements/docs:
contextgit relevant-for-file <path> # Find related requirements contextgit extract <ID> # Get precise context -
After modifying requirements/docs:
contextgit scan docs/ --recursive # Update the index contextgit status --stale # Check for broken links -
When adding new requirements:
contextgit next-id <type> # Generate ID (business, system, architecture, code, test) # Add YAML frontmatter with the generated ID contextgit scan docs/ --recursive # Register in index -
When upstream requirements change:
contextgit status --stale # Find affected downstream items # Update downstream items as needed contextgit confirm <ID> # Mark as synchronized
Detection
Check for .contextgit/config.yaml to confirm this is a contextgit-managed project.
Project Overview
contextgit is a local-first, git-friendly CLI tool for managing requirements and context traceability in LLM-assisted software projects.
Current Status: v1.1.0 - Production ready, all 10 CLI commands implemented.
What contextgit Is
contextgit is a local-first, git-friendly CLI tool that:
- Tracks requirements traceability from business needs → system specs → architecture → code → tests
- Embeds metadata in Markdown files (YAML frontmatter or HTML comments)
- Maintains a central YAML index (
.contextgit/requirements_index.yaml) - Detects staleness via checksums when upstream requirements change
- Extracts precise context snippets for LLM consumption
- Provides JSON output for all read operations to support Claude Code workflows
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.
- 6d ago First seen · 226 lines · 2,280 tokens per session scan A 8fd593a4562b
ContextGit CLAUDE.md is an instructions file published in the GitHub repository Mohamedsaleh14/ContextGit (10 stars, last pushed 9mo ago), licensed MIT. It adds 2,280 tokens to every session, about $0.0114 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
puppyone AGENTS.md
Instructions for puppyone-ai/puppyone, covering puppyone (contextbase), connect, collaborate, platform and active development directories.
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
aiduMEI AGENTS.md
AGENTS.md instructions for monkey2jack/aiduMEI, covering agents.md — deploy, verify, operate aidumei, choose your engine mode, one-line prompt (canonical), install and start and prove memory is actually working.
ai-context-kit AGENTS.md
AGENTS.md instructions for MSiccDev/ai-context-kit, covering ai context kit agent guide, purpose, source of truth and precedence, repository map and scope and precedence for agents.md files.
titen AGENTS.md
Instructions for RamaAditya49/titen, covering agents.md, product, repository stage, required work lifecycle and coding constraints.
titen CLAUDE.md
Instructions for RamaAditya49/titen, covering claude.md, read agents.md first, commands, two runtimes, one core and publishing to npm.