Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tomzx/agentsnpx agentmods add skills/tomzx/agents/review-implementationWrote 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/tomzx/agents/review-implementation)<a href="https://agentmods.dev/skills/tomzx/agents/review-implementation"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-implementation/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/tomzx/agents/review-implementation"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.01547 |
| Opus 5 | $0.00012 | $0.00773 |
| Sonnet 5 | $0.00005 | $0.00309 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
review-implementation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Implementation
Audits a code implementation and reports findings across eight categories: correctness, code quality, test coverage, security, performance, spec alignment, reversibility, and forward compatibility. Each finding is prioritized with 🔴 MUST fix, 🟡 SHOULD fix, or 🟢 MAY fix.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. - Code to review provided in context, as file paths to read, or as a diff
- Specification or acceptance criteria (optional, improves alignment check)
.sdlc/features/N-<slug>/lifecycle.md(optional, if a lifecycle document was produced): verify state machines, transition guards, invariants, and retention policies are implemented correctly.sdlc/features/N-<slug>/telemetry.md(optional, if a telemetry plan was produced): verify analytics events are implemented correctly.sdlc/features/N-<slug>/observability.md(optional, if an observability plan was produced): verify logging, metrics, tracing, and health checks are implemented correctly
Steps
- Read the code thoroughly.
- Cross-reference against the specification or acceptance criteria if provided.
- Identify issues in each category below.
- Prioritize each finding: 🔴 MUST, 🟡 SHOULD, 🟢 MAY.
- Report findings using the output format. Omit categories with no findings.
- Write the findings to
.sdlc/features/N-<slug>/review-implementation.mdwith frontmatterartifact: implementation,verdict(approvedif there are no blocking findings,changes-requestedif the author must address findings,rejectedfor a fundamental flaw), andreviewed_at: <ISO date>, and the findings as the body, perskills/sdlc/references/shared.md. Record any unresolved open questions in the findings body.
Review Checklist
Correctness
- Does the implementation meet all acceptance criteria?
- Are edge cases and error conditions handled?
- Are there logic errors, off-by-one errors, or incorrect conditionals?
- Is state managed correctly (no races, no stale data)?
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.
- 6d ago First seen · 172 lines · 24 tokens per session scan A 2208ad16bdd7
review-implementation is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,547 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.