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/mimfort/rag_for_git/agents-mdgit clone --depth 1 https://github.com/mimfort/rag_for_gitWhat 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 | $0.00640 | $0.00640 |
| Opus 5 | $0.00320 | $0.00320 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
rag_for_git AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rag_for_git — Codex CLI context
See CLAUDE.md for the full architecture, commands, and invariants.
Install or update rag-reviewer for Codex
uvx --from rag-reviewer@latest reviewer install codex
uvx --from rag-reviewer@latest reviewer install codex --dry-run
uvx --from rag-reviewer@latest reviewer install codex --no-skills
uvx --from rag-reviewer@latest reviewer install-skills codex
The first command manages one global reviewer MCP server and the namespaced
rag-reviewer plugin. Re-running it upgrades the marketplace/plugin. Dry-run is
read-only and offline; install-skills codex leaves MCP untouched.
Verify the result:
codex plugin list --json
codex mcp list
Success means rag-reviewer is installed and enabled and codex mcp list contains exactly one
reviewer. Identified legacy skills are moved to
$CODEX_HOME/reviewer-legacy-backups/<timestamp>; modified or ambiguous copies stay untouched.
Failures print the config backup path. Open a New Chat/new CLI session after installation; in an
IDE, also use Reload Window.
Companion global install for Claude Code
uvx --from rag-reviewer@latest reviewer install claude-code
uvx --from rag-reviewer@latest reviewer install claude-code --no-skills
claude plugin list --json
claude plugin marketplace list --json
The default command manages the enabled user-scope rag-reviewer plugin from
https://github.com/mimfort/rag_for_git.git, so it works from every project and current
directory. --no-skills installs only the global MCP server. Verify that plugin list contains
the enabled rag-reviewer@rag-reviewer-marketplace entry with user scope; the optional
marketplace listing should show the exact HTTPS source. Open a New Chat/new CLI session after
installation; in an IDE, also use Reload Window.
Skills
Every directory under plugin/skills/ containing SKILL.md is registered in the
rag-reviewer namespace. _common and nested references are delivered as support files, not
registered skills.
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.
- 2d ago First seen · 71 lines · 640 tokens per session scan A 703c8cc24e40
rag_for_git AGENTS.md is an instructions file published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 2d ago), licensed MIT. It adds 640 tokens to every session, about $0.0032 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
roam-code AGENTS.md
Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
code-graph AGENTS.md
Instructions for FalkorDB/code-graph, covering codegraph - agent instructions, architecture, data flow, directory structure and commands.
VinvAI AGENTS.md
Instructions for VinvAI/VinvAI, covering agents.md, what this repo is, code map — edit the source, not the artifacts, setup and verify before you hand back a diff.
agentmap AGENTS.md
Instructions for raymondchins/agentmap, covering agentmap — project instructions, ⚠️ this is a public oss repo, not one of ray's apps, read before editing, layout and hard invariants.
m1nd AGENTS.md
Instructions for maxkle1nz/m1nd, covering agents.md — working guide for any coding agent on m1nd, the gates (must pass — these are the ci), git identity — absolute, no-leak — reputation rule (public repo) and how work lands — bursts, not pr-per-fix.
CodeStory AGENTS.md
Instructions for TheGreenCedar/CodeStory, covering codestory agent guide, start here, ownership boundaries, product invariants and identity and configuration.