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 skills add mhmdreza-rafiei/agent-tools --skill reviewgit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/skills/mhmdreza-rafiei/agent-tools/review)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/review"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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/skills/mhmdreza-rafiei/agent-tools/review"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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 | $0.00115 | $0.00765 |
| Opus 5 | $0.00057 | $0.00382 |
| Sonnet 5 | $0.00023 | $0.00153 |
| Haiku 4.5 | $0.00012 | $0.00076 |
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 8d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building is not done when the code runs. It is done when the code is correct. AI moves fast, and fast means things get built that work on the surface but drift from the architecture, violate the design system, or miss edge cases. This skill catches those before they compound.
Run after every feature, before moving on. It reports — it does not fix. (This makes it safe to run unattended in automated flows: it never changes code, it surfaces findings.)
Step 1 — Establish the benchmark
From the context system: context/plan.md (the /architect plan for this work) and the task given; context/architecture.md (boundaries, systems, rules); context/standards.md (naming, structure, conventions); context/design-system.md + context/design/ and context/memory/ui-registry.md for UI. No plan on record? Ask what the feature was meant to do — you can't verify correctness without knowing what correct looks like.
Step 2 — Review in three layers
Layer 1 — Plan alignment. Does it do what plan.md said, no more, no less? Flag anything planned-but-missing and built-but-unplanned.
Layer 2 — System integrity (where AI drift hides). Architecture boundaries respected (right code in the right place)? Design system used (correct tokens, no hardcoded values, matches ui-registry.md)? Code standards followed (naming, structure, types, error handling)? Any new pattern where an existing one should've been reused?
Layer 3 — Production readiness. Error handling present (not silent failure)? Empty/loading/missing-data edge cases handled? Console/terminal errors? Obvious bugs a real user would hit?
Step 3 — Report
## Review — [Feature]
### Layer 1 — Plan alignment [PASS / ISSUES]
### Layer 2 — System integrity [PASS / ISSUES] (cite the context file each issue breaks)
### Layer 3 — Production readiness [PASS / ISSUES]
### Summary
[X] issues across [Y] layers. [If none: ready to ship. If issues: resolve before moving on.]
Label each issue with severity:
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.
- 8d ago First seen · 49 lines · 115 tokens per session scan A 45be1dfb5631
review is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 115 tokens to every session and 765 once invoked, about $0.0006 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…