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.
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/rules/mhmdreza-rafiei/agent-tools/ai-attribution)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/ai-attribution"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/ai-attribution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/ai-attribution"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/ai-attribution.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01070 | $0.01070 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
ai-attribution 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI git attribution (Cursor and other agents)
What "AI contribute" means
Some tools add machine authorship to commits so GitHub can show an AI as a contributor:
- Trailer (most common): a blank line, then something like:
Co-authored-by: Cursor <...>Co-authored-by: Claude <...>Co-authored-by: GitHub Copilot <...>
- Author / committer identity:
Author:orCommitter:set to an agent name/email (e.g. Cursor Agent) instead of the human.
Trailers live in the commit message. Changing only future commits does not rewrite old history. GitHub's Contributors list can lag after a rewrite.
Default policy
- Prefer human-only authorship unless the user explicitly wants AI co-author trailers.
- Never add
Co-authored-by:for Cursor, Claude, Copilot, or other agents unless asked. - Never rewrite git history, force-push, or amend published commits unless the user explicitly asks and understands the risk.
- Before any history rewrite: full backup of
.git(or a clearly named sibling backup), then confirm backup exists.
Prevent (do this first)
- Cursor: Settings -> Agents -> Attribution -> turn off (stops new Cursor co-author injection).
- Optional local guard --
.git/hooks/prepare-commit-msg(strip known AI trailers on every commit):
#!/bin/sh
MSG_FILE=$1
# Drop AI co-author lines (extend patterns as needed)
sed -i.bak -E '/^Co-authored-by:.*(Cursor|Claude|Copilot|ChatGPT|Gemini|Codex).*/Id' "$MSG_FILE"
rm -f "${MSG_FILE}.bak"
On Windows Git Bash, sed -i works; for PowerShell-only setups, use a small Node/Python stripper instead. Make the hook executable (chmod +x on Unix).
- Confirm
git config user.name/user.emailare the human's (do not changegit configunless the user asks).
Detect
# Trailers in reachable history
git log --all --grep='Co-authored-by:' -i
# Agent as author/committer
git log --all --format='%H %an <%ae> | %cn <%ce> | %s' | grep -iE 'cursor|claude|copilot|chatgpt|gemini|codex'
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.
- 9d ago First seen · 88 lines · 1,070 tokens per session scan A 9c2f23868dbb
ai-attribution is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 21d ago), licensed MIT. It adds 1,070 tokens to every session, about $0.0053 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 cursor rules, from other repositories
git
Conventional commit message format for git commits.
git-commit-attribution
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
commit-sponsors
Every git commit message must acknowledge BetterDesk supporters.
conventional-commits
Use the Conventional Commit Messages specification to generate commit messages.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.
git-commit-standards
Enforce structured Git commit messages.