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/n-shadloo/git-authoring/agents-mdgit clone --depth 1 https://github.com/n-shadloo/git-authoringWhat 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 | $0.10785 | $0.10785 |
| Opus 5 | $0.05393 | $0.05393 |
| Sonnet 5 | $0.02157 | $0.02157 |
| Haiku 4.5 | $0.01078 | $0.01078 |
Grade A, and why
git-authoring 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 — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git authoring conventions
Commit-message and pull-request conventions for this repository. Applies to any agent or contributor writing a git commit or opening a pull request here.
By default, turn staged changes into a commit command a reader will thank you for six months from now: read what is actually staged, work out the intent behind the change, and present an exact quoted-heredoc command containing a Conventional Commits message with an accurate type, a well-chosen scope, an imperative subject, and — when the change warrants it — a body that explains why plus footer trailers that carry metadata. When asked, also choose which unstaged files belong together and present staging plus commit commands, write complete pull-request content, write the release note for a version, review an incoming pull request and hand the maintainer the text to paste, work the repository itself — branches, rebases, conflicts, recovery — or carry out staging, committing, and pushing. Getting the shape right (type(scope): subject) is table stakes. The value is in choosing the right type, writing a subject that says what changed, and recording the reasoning the diff itself can't show.
Usage modes
Choose exactly one mode from the user's request.
- Already-staged commit (default): inspect the staged diff and present the exact heredoc commit command for the user to run.
- Choose files: select one coherent set and present exact staging commands followed by the heredoc commit command for the user to run.
- Pull request: write a title and structured Markdown description from the branch diff. Do not open it.
- Autonomous stage, commit, and push: run those operations end to end only when the user unmistakably asks the agent to do the work itself, such as "stage, commit, and push this for me" or "do it all yourself." On a further explicit request, this mode may also tag and publish a release.
- Release note: establish the range since the last release, read what actually landed, and write the note as a Markdown block. Do not tag, publish, or write a file.
- Review an incoming pull request: read someone else's PR through
gh, work the decision through with the user, and write the review comment or the merge-commit message as a Markdown block for them to paste. Do not approve, request changes, comment, or merge. - Repository operations: branches, merges and rebases, history editing, undo, moving work, conflict resolution, and recovery. Read the real state, say what the situation is, and present the exact commands. Execute only under the mode 4 request.
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 · 527 lines · 10,785 tokens per session scan A 705b5829e66d
git-authoring AGENTS.md is an instructions file published in the GitHub repository n-shadloo/git-authoring (4 stars, last pushed 6d ago), licensed MIT. It adds 10,785 tokens to every session, about $0.0539 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
claude-codex-settings CLAUDE.md
Claude Code instructions for fcakyon/claude-codex-settings, covering claude-settings, repo structure, cross-tool plugin format reference, plugin manifests and root marketplace files.
claude-codex-settings AGENTS.md
AGENTS.md instructions for fcakyon/claude-codex-settings, a project described as: Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
claude-codex-settings GEMINI.md
Gemini CLI instructions for fcakyon/claude-codex-settings, a project described as: Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.