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 commands/ofershap/think-first/review-approachgit clone --depth 1 https://github.com/ofershap/think-firstWrote 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/ofershap/think-first/review-approach)<a href="https://agentmods.dev/commands/ofershap/think-first/review-approach"><img src="https://agentmods.dev/badge/commands/ofershap/think-first/review-approach.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 | $0.00013 | $0.00156 |
| Opus 5 | $0.00006 | $0.00078 |
| Sonnet 5 | $0.00003 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
review-approach 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.
What it actually says
Review the current implementation approach:
- What was the goal? Restate the original requirement.
- What was done? Summarize the changes made so far.
- Does it solve the problem? Evaluate whether the implementation actually addresses the requirement.
- What could be improved? Identify any issues, missed edge cases, or better approaches.
- What's missing? Are there tests, error handling, or documentation that should be added?
- Side effects? Did the changes break or affect anything else?
Be honest and specific. If the approach is wrong, say so and suggest a better one.
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 · 17 lines · 13 tokens per session scan A 26fc0e80a226
review-approach is a command published in the GitHub repository ofershap/think-first (0 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 156 once invoked, about $0.0001 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 commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
create_handoff
Create handoff document for transferring work to another session.