Borrowing it
Nothing to install: this file belongs to mag123c/toktrack. 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/mag123c/toktrack/main/.claude/skills/review/SKILL.mdgit clone --depth 1 https://github.com/mag123c/toktrackWrote 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/mag123c/toktrack/review)<a href="https://agentmods.dev/skills/mag123c/toktrack/review"><img src="https://agentmods.dev/badge/skills/mag123c/toktrack/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/mag123c/toktrack/review"><img src="https://agentmods.dev/badge/skills/mag123c/toktrack/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 78 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00034 | $0.01135 |
| Opus 5 | $0.00017 | $0.00567 |
| Sonnet 5 | $0.00007 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
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 10d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review (toktrack override)
Follows the global /review multi-agent pattern, with the following overrides:
Override: UX Review Inactive
This project is a terminal TUI app — do not run the UX Review Agent. Run Code Review Agent only.
Override: Code Review Checklist Extension
In addition to the global checklist, append the following to the Code Review Agent prompt:
Critical (PLAN gate)
| Category | Items |
|---|---|
| PLAN assumption refutation | Does the diff falsify the [agent-inferred]/[unverified-gate] assumptions from the PLAN (falsified → P1+, carry to wrap) |
Author Review Gate (P0 — Identity / Matrix)
This repo is OSS and the reviewer is the author (receiving PRs). Generic code health is covered by Rust/TUI/clippy below; this section examines product-specific risks that only the author can validate. Perspective SSOT: session memory feedback_review_perspective.md.
| Tier | Category | Items |
|---|---|---|
| reject | Identity ① ultra-fast | Adding latency·blocking IO·synchronous network to hot path/startup → reject |
| reject | Identity ② persistent cache / data preservation | Risk of cache·history loss or corruption → reject. backward-compat·graceful degradation are the means to uphold this |
| ruthless | Irreversible | breaking change · data migration · public behavior change |
| ruthless | Environment/state matrix (contributors test only their own machine) | OS(paths·home·file locks·Windows) / source schema version(forward new-schema+backward old-format, new source·parser PRs require old-version·unknown-schema fixture) / data shape(empty·large·corrupt·partial·permissions) / locale·TZ·DST / concurrency(read race while source file is being written) / terminal(width·color·TERM) / first-run vs upgrade migration |
| bias to YES | Other features·ideas | Stars are the goal — acceptance bias. But if it taxes either core(weighing down hot path·startup·cache paths), request location·approach adjustment only. additive/opt-in/lazy/behind a flag = welcome |
| lenient | Style·naming preferences | Linter takes precedence, bikeshed prohibited (uniform strictness = contributor friction → star loss) |
| signal | Direction/growth fit (not a gate) | Beyond code quality·conventions, every contribution(issue·PR) also gets a direction-fit verdict in the review output: strengthens wedge (persistent cache/data preservation) / neutral (additive) / dilutes focus (e.g. feature-parity chasing) + 1–2 lines of rationale. Weigh holistically: maintenance cost vs value, real value to target users(AI CLI heavy users), contribution to project direction. Never a reject reason — the two identities above remain the only gates, bias-to-YES stands |
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.
- 10d ago First seen · 89 lines · 34 tokens per session scan A e7eefc989a6b
review is a skill published in the GitHub repository mag123c/toktrack (189 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,135 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 2026-08-30.
Other skills, from other repositories
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.
plan-review-architecture
Architecture-dimension reviewer for written plans. Use when running plan-review or directly when an architectural review is wanted. Activate for keywords like "architecture review", "data flow", "failure modes", "rollback", "edge cases", "test matrix". Scores 5 sub-dimensions 0-10, produces ranked fixes. Always cite…
code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…