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/Chia-Network/cadtWrote 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/chia-network/cadt/commit-messages)<a href="https://agentmods.dev/rules/chia-network/cadt/commit-messages"><img src="https://agentmods.dev/badge/rules/chia-network/cadt/commit-messages/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/chia-network/cadt/commit-messages"><img src="https://agentmods.dev/badge/rules/chia-network/cadt/commit-messages.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 | $0.00320 | $0.00320 |
| Opus 5.5 | $0.00128 | $0.00128 |
| Sonnet 5.5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
commit-messages 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 1mo 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.
What it actually says
Commit Message Format
Commitlint enforced. Format: type(SCOPE): subject
Type (required)
feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert
Scope (optional)
UPPER-CASE only. Example: fix(API):, feat(V2):
Subject (required)
- Present-imperative tense ("add feature" not "added feature")
- No capitalized first letter, no trailing period
- Under 72 characters
Body/Footer (optional)
- Body: blank line after subject, explain "why" not "what", wrap at 72 chars
- Footer:
Fixes #123,Closes #456, orBREAKING CHANGE: description
Examples
fix: correct MySQL mirror numeric comparison for DECIMAL fields
feat(V2): add batch commit verification for live API tests
fix: handle DECIMAL precision in MySQL mirror verification
MySQL returns DECIMAL fields with full precision (e.g., 1000.000000)
while expected values may have fewer decimal places. Add numeric
comparison to compare values as numbers when both are valid numbers.
feat(API): change response format for pagination
BREAKING CHANGE: pagination response now uses 'items' instead of 'data'
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.
- 1mo ago First seen · 52 lines · 320 tokens per session scan A 7d27d41b5d56
commit-messages is a cursor rule published in the GitHub repository Chia-Network/cadt (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 320 tokens to every session, about $0.0013 per session on Opus 5.5. 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 2026-09-04.
Other cursor rules, from other repositories
git
Git workflow — commit format, push policy, and PR process.
commit-sponsors
Every git commit message must acknowledge BetterDesk supporters.
commits
Conventional Commits standards for clear, semantic commit messages.
no-ai-contributors
Never add AI tools as git authors or project contributors.
conventional-commits
Use the Conventional Commit Messages specification to generate commit messages.
git-discipline
Commit, push, and branching rules. Owns ALL git behavior; other files state only their deviations.