Borrowing it
Nothing to install: this file belongs to KeepSoftwareSimple/compass-calendar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/KeepSoftwareSimple/compass-calendar/main/.github/prompts/review.mdgit clone --depth 1 https://github.com/KeepSoftwareSimple/compass-calendarWrote 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/commands/keepsoftwaresimple/compass-calendar/review)<a href="https://agentmods.dev/commands/keepsoftwaresimple/compass-calendar/review"><img src="https://agentmods.dev/badge/commands/keepsoftwaresimple/compass-calendar/review/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/commands/keepsoftwaresimple/compass-calendar/review"><img src="https://agentmods.dev/badge/commands/keepsoftwaresimple/compass-calendar/review.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 | $0.00000 | $0.00318 |
| Opus 5.5 | $0.00000 | $0.00127 |
| Sonnet 5.5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
review 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.
What it actually says
Agent review prompt
You are reviewing a Compass pull request as a stranger to it. You have not seen the implementer's reasoning and must not use the PR description as evidence. Do not edit any file. Do not run tests; CI does that.
Steps
- Read
AGENTS.md. - Run
gh pr diff <number>(orgit diff <base>..<head>) and read the complete diff. If it is empty, comment "agent-review: empty diff" and stop. - Read enough surrounding source to judge each hunk in context.
- Look for: state and race defects, missing cleanup, boundary violations
(contracts outside
packages/core, provider-name branches, barrels), keyboard and focus regressions, accessibility, auth and privacy, data loss, weakened tests, em-dashes in user-facing strings. - Report only confirmed, actionable findings with a path and line. Uncertain items are questions, listed separately and briefly.
Output
Post exactly one comment with gh pr comment <number> --body:
agent-review: findings | no confirmed findings
FINDINGS
- severity: high|med|low
path: file:line
impact: ...
evidence: ...
QUESTIONS
- ...
Omit empty sections. A high finding means the PR should not merge as is;
say so in one sentence at the top. Never post "looks good" without having
read the whole diff.
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.
- yesterday First seen · 40 lines · 0 tokens per session scan A b500015bd47c
review is a command published in the GitHub repository KeepSoftwareSimple/compass-calendar (226 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 318 tokens. 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 2026-11-07.
review compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reviewKeepSoftwareSimple/compass-calendar | Command | 226 | today | MIT | A | 0 | GitHub Copilot |
| pr-readycostajohnt/oss-autopilot | Command | 28 | 5d ago | MIT | A | 45 | Claude Code |
| push-changesbartstc/vite-ts-react-template | Command | 123 | 15d ago | MIT | A | 0 | Claude Code |
| prepare-releasesaeedkolivand/ai-job-hunter-app | Command | 63 | yesterday | Apache-2.0 | A | 20 | Claude Code |
| create-PRbartstc/vite-ts-react-template | Command | 123 | 15d ago | MIT | A | 0 | Claude Code |
| quality-commandsJNTMTMTM/eIsland | Command | 335 | yesterday | GPL-3.0 | A | 0 | Claude Code |
| review-codechohra-med/expo_boilerplate | Command | 36 | 1mo ago | MIT | A | 50 | Claude Code |