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/maxedapps/agent-skills/code-reviewnpx skills add maxedapps/agent-skills --skill code-reviewgit clone --depth 1 https://github.com/maxedapps/agent-skillsWhat 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 | $0.00064 | $0.00834 |
| Opus 5 | $0.00032 | $0.00417 |
| Sonnet 5 | $0.00013 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
code-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 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Hard rules
- Scope from user/task only. Unclear → ask. Don’t widen.
- Inspect thoroughly; report selectively. Candidate ≠ finding.
- “No material findings” is valid.
- No source edits unless asked. Don’t clobber owner git/worktree state.
- Main agent assigns final findings/scores/verdicts. Child handoffs = evidence.
- Delegate by default into bounded read-only lanes when safe. “Small/easy” ≠ skip.
- Leverage subagents — built-in, extensions/plugins, or skills. Follow
use-subagentspolicy; use the host’s selected launcher (on Pi without nativesubagent_*,use-pi-subagents).
Admit a finding only if
- concrete failure
- realistic reachability
- practical impact
- safeguards considered
- action justified now
Omit nits, hypotheticals, and low-impact noise. Don’t hide them in caveats.
Loads
| When | Read |
|---|---|
| Broad or deep dimension review, or explicit test/validation review | references/review-dimensions.md first |
| Vs plan/tracker/design/acceptance | references/plan-backed-review.md first |
| Standalone report | assets/review-report-template.md before write |
Flow
- Fix scope/authority/output — ask if needed.
- Load conditional resources.
- Inspect targets, callers, tests, config, diffs. Note skips + confidence limits.
- Delegate review lanes by default (correctness, security, tests, plan-matrix, …).
- Run checks/repros that raise confidence; preserve owner state.
- Admit → score → cap findings.
- Optional
decomplexonly if complexity-focused and report writable; else built-in simplicity. Don’t merge contracts. - Write
.reviews/<slug>.md(unless chat-only/no-write) or return handoff. - Cleanup any workflow runtime/process state.
Scores and caps
| Severity | S4 critical · S3 high · S2 medium · S1 low · S0 optional |
| Confidence | C3 confirmed · C2 supported · C1 tentative (not a finding yet) |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 86 lines · 64 tokens per session scan A e67cbb613489
code-review is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 18d ago), licensed MIT. It adds 64 tokens to every session and 834 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…