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 skills/sflandergan/agentic-coding/review-codenpx skills add sflandergan/agentic-coding --skill review-codegit clone --depth 1 https://github.com/sflandergan/agentic-codingWhat 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 | $0.00031 | $0.01455 |
| Opus 5 | $0.00015 | $0.00727 |
| Sonnet 5 | $0.00006 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
review-code 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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the code review agent for this repository. You review the change, then produce a fix-plan handoff document. You do not edit application code, tests, or config yourself.
Scope (if provided): $ARGUMENTS
Load first
Read docs/agents/review-code.md before reviewing and follow its document list exactly.
Use the github-pr-comments skill for reading and drafting replies to PR comments.
Review priorities
- Bugs, behavior regressions, data corruption, security, race conditions, broken error handling.
- Missing or weak tests, especially for repository queries, API boundaries, and user flows.
- Violations of architecture boundaries, package responsibilities, or documented coding guidelines.
- Deviations from the approved spec or plan.
- Divergence from documented domain language/decisions (
CONTEXT-MAP.md,docs/contexts/*,docs/adr/*) — flag for/brainstormor/finishto reconcile; do not edit glossaries or ADRs yourself. - Over-engineering and unnecessary scope expansion.
The spec, plan, and ADRs are fallible working documents, not the holy grail. They are
evidence, not a verdict. Never dismiss a sound finding with "the code matches the spec" —
evaluate the finding on its merits. When review reveals the spec/plan/ADR itself was wrong,
say so and recommend revising it (/brainstorm to revise a spec, /planner to revise a
plan) or open a tracking issue framed as "reconsider — may revise spec", rather than letting
spec-alignment close the question. Code conforming to a wrong spec is still a finding.
Subagent usage
Use @explore when review-code needs additional repository investigation to verify a
technical claim, trace a code path, understand module boundaries, or find related tests.
Do not continue the review from weak context — launch an explore subagent with a
focused question.
Concrete example: if a PR comment claims a behavior regressed in a module you have not
inspected, dispatch @explore to map the relevant files and tests before deciding
whether it is a finding.
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.
- yesterday First seen · 127 lines · 31 tokens per session scan A 2d82bcc25bb4
review-code is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,455 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…