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 rules/pueraeternis/agentic-project-template/04-review-and-commitgit clone --depth 1 https://github.com/pueraeternis/agentic-project-templateWrote 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/pueraeternis/agentic-project-template/04-review-and-commit)<a href="https://agentmods.dev/rules/pueraeternis/agentic-project-template/04-review-and-commit"><img src="https://agentmods.dev/badge/rules/pueraeternis/agentic-project-template/04-review-and-commit.svg" alt="Measured on agentmods" 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 | $0.00546 | $0.00546 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
04-review-and-commit 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 4d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and Completion
Implementation is not complete until it has been:
- validated;
- independently reviewed;
- documented;
- accepted.
Review is a mandatory engineering stage of the project lifecycle.
Completion Workflow
Plan Implementation
↓
Validation
↓
Code Review
↓
Documentation Update
↓
Progress Update
↓
Commit
Do not skip review unless explicitly instructed.
Review Scope
Review the implementation against:
- the approved implementation plan;
PROJECT.md;ROADMAP.md;ARCHITECTURE.md;ENGINEERING.md;- relevant ADRs;
- acceptance criteria.
Focus on:
- correctness;
- completeness;
- maintainability;
- engineering consistency;
- architectural compliance;
- scope compliance.
Scope Verification
Confirm that:
- only approved functionality has been implemented;
- no undocumented functionality has been introduced;
- architectural boundaries have been respected;
- engineering conventions have been followed;
- implementation remains within the approved scope.
Reject unnecessary scope expansion.
Documentation Verification
Before completing the work, verify whether updates are required for:
ARCHITECTURE.md;ENGINEERING.md;- ADRs;
- implementation plans;
RUNBOOK.md;PROGRESS.md.
Repository knowledge should remain internally consistent.
Validation
Perform all project-required validation.
Typical validation includes:
- formatting;
- linting;
- type checking;
- automated tests;
- manual verification.
Use the validation commands documented in ENGINEERING.md.
Progress Update
When implementation is approved:
- update
PROGRESS.mdwhen appropriate; - complete the implementation checklist;
- move completed plans according to the documented plan lifecycle.
Project history should accurately reflect completed work.
Commits
Create commits only when explicitly requested.
Before committing, verify:
- validation has completed successfully;
- documentation is synchronized with implementation;
- review findings have been addressed;
- no temporary code remains;
- the repository is internally consistent.
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.
- 4d ago First seen · 157 lines · 546 tokens per session scan A a6cc92a941e7
04-review-and-commit is a cursor rule published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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
辅助生成 git 提交信息.
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
git-commit
Use this when the user asks for a git commit, commit message, or commit command.
git-authoring
Conventional Commit, pull-request, release-note, and PR-review conventions for this repository.
no-tool-contributors
Never add AI coding tools as contributors or co-authors.