ai-commit-attribution

A Git commit rule that records when artificial intelligence materially helped create the change. Git commits are saved records of changes to a codebase.

In plain words
What is it for?
Use it before creating commits that were substantially shaped by an AI coding tool. The commit message includes the required product and model details when known.
Why use it?
It makes AI assistance visible to people reviewing the project and follows the repository's contribution rules. It avoids falsely presenting the AI as a co-author.

Cursor rule for Cursor

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 rules/partikularwaters/banka/ai-commit-attribution
Clone the repo
git clone --depth 1 https://github.com/partikularwaters/Banka

Made for: Cursor.

Per session 104 This file is loaded in full into every session.
When invoked 104 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 $0.00104 $0.00104
Opus 5 $0.00052 $0.00052
Sonnet 5 $0.00021 $0.00021
Haiku 4.5 $0.00010 $0.00010

Measured yesterday against content hash 7d88083afae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-commit-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 yesterday.

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.

.cursor/rules/ai-commit-attribution.mdc · 17 lines

What it actually says

AI Commit Attribution

Before creating a commit, follow the AI assistance attribution convention in CONTRIBUTING.md. When your work materially shaped the commit, add this trailer to the commit-message body using your actual product and model when known:

Assisted-by: <provider or product> (<model, if known>)

Do not invent an AI email address or substitute Co-authored-by.

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. yesterday First seen · 17 lines · 104 tokens per session scan A 7d88083afae1

Subscribe to this mod's changes

ai-commit-attribution is a cursor rule published in the GitHub repository partikularwaters/Banka (3 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session, about $0.0005 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.