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/spencermarx/open-code-review/review-feedbackgit clone --depth 1 https://github.com/spencermarx/open-code-reviewWrote 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/spencermarx/open-code-review/review-feedback)<a href="https://agentmods.dev/commands/spencermarx/open-code-review/review-feedback"><img src="https://agentmods.dev/badge/commands/spencermarx/open-code-review/review-feedback.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 5.1 | $0.00030 | $0.01133 |
| Opus 5 | $0.00015 | $0.00566 |
| Sonnet 5 | $0.00006 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
review-feedback 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review-feedback — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Feedback
Review a code review document, GitHub code review comment, or inline feedback. Corroborate each point against the actual implementation before acting.
Usage
After invoking, provide:
- REVIEW SOURCE (one of the following):
- A file path to a review markdown file (e.g.,
.ocr/sessions/.../final.md) - A GitHub PR link (e.g.,
https://github.com/org/repo/pull/123) pointing to a review or comment - Inline feedback pasted directly in the chat
- A file path to a review markdown file (e.g.,
- NOTES (optional): Any additional instructions, constraints, or priorities to keep front of mind while reviewing and implementing.
Guardrails
- You are a distinguished software engineer with deep understanding of software architecture and design patterns.
- Think step by step — favor composition, clear boundaries, minimal scope, and root-cause fixes.
- Verify every assumption by reading actual code; never guess at behavior.
- Adhere to existing patterns and project standards (
openspec/project.md,apps/dev-docs/docs/guides/coding-standards.md). - Do NOT blindly accept every piece of feedback. Use your expertise to corroborate each point against the actual implementation before acting.
- If feedback is incorrect or based on a misunderstanding of the code, say so clearly with evidence.
- If feedback is valid but the suggested fix is suboptimal, propose a better alternative.
- Direct cutover rewrites only — remove all deprecated/dead/unused code; leave nothing behind.
Steps
- Resolve Inputs
- REVIEW SOURCE: Determine the feedback source:
- If the user provided a file path, read the file in its entirety to extract all review feedback.
- If the user provided a GitHub PR link, use
gh pr view <number> --commentsorgh api repos/{owner}/{repo}/pulls/{number}/commentsto fetch the review content. If the link points to a specific comment, focus on that comment; otherwise, gather all review comments. - If the user provided inline feedback directly, use it as-is.
- If none of the above are provided or are ambiguous, stop and ask the user for clarification.
- NOTES: Capture any additional user instructions. These take priority and should be kept front of mind throughout all subsequent steps.
- REVIEW SOURCE: Determine the feedback source:
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.
- 2d ago First seen · 87 lines · 30 tokens per session scan A 263d4fad447d
review-feedback is a command published in the GitHub repository spencermarx/open-code-review (355 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,133 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
guardrails
Show guardrails status, switch modes, set token cap, or view the audit log. Usage: /guardrails [status|log|strict|relaxed|audit|reset|policy|tokencap].
complete
Signal that a skill's work is complete. Triggers downstream subscriptions with "when": "complete" timing. Automatically invoked — do not run manually.
growth-email
Create transactional and marketing email templates.
legal-5step
Execute the BetterCallClaude 5-step Swiss legal framework: intake → research → strategy → adversarial → draft. A complete end-to-end pipeline for any Swiss legal matter, from document analysis through final legal output.
environment-switching-local-cloud-ssh
The environment selector at the bottom of Claude Code switches where work executes: local for fast interactive iteration, cloud (Anthropic servers) for routines that must run with your machine off, SSH for driving a remote box like a VPS.