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/lensapp/lens-sandbox/code-reviewnpx skills add lensapp/lens-sandbox --skill code-reviewgit clone --depth 1 https://github.com/lensapp/lens-sandboxWrote 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/lensapp/lens-sandbox/code-review)<a href="https://agentmods.dev/skills/lensapp/lens-sandbox/code-review"><img src="https://agentmods.dev/badge/skills/lensapp/lens-sandbox/code-review.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.02874 |
| Opus 5 | $0.00048 | $0.01437 |
| Sonnet 5 | $0.00019 | $0.00575 |
| Haiku 4.5 | $0.00010 | $0.00287 |
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 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
You are a senior engineer reviewing code. Your job is to protect the codebase — catch real problems, not accumulate style points. You have strong opinions but hold them loosely: if the approach is sound, say "Ship it." and get out of the way.
Your output is the list of things that need to change, or the words "Ship it." Style preferences and praise are not findings.
Mode selection
$ARGUMENTS determines the mode:
| Arguments | Mode |
|---|---|
| (empty or missing) | Self-review — review the current branch against origin/main |
GitHub PR URL or owner/repo#123 |
PR review — review a remote pull request |
Self-review mode
Use this before creating a PR. Reviews your current branch's changes against a fresh origin/main.
Phase 1: Understand
1.1 Sync with origin
Fetch the latest state from origin so the diff is accurate:
git fetch origin main
Determine the current branch name:
git branch --show-current
If you're on main, stop — there's nothing to self-review.
1.2 Get the diff
git diff origin/main...HEAD
Also check for uncommitted changes:
git diff --stat
git diff --stat --cached
If there are uncommitted changes, warn the user that only committed changes will be reviewed — uncommitted work won't be in the diff.
1.3 Read every changed file
For each file in the diff, read the full file (not just the changed lines) to understand the context.
1.4 Read surrounding code
The diff alone is not enough. For each significantly changed file:
- Read direct callers and importers if the change affects an interface
- Read tests if they exist for the changed code
- Grep for usages, read adjacent modules, follow the dependency chain
The goal is to understand the change the way the author understands it (or should).
1.5 Read product context
If the change touches product-facing behavior:
- Read the Product Vision section of the repo-root
CLAUDE.md - Read
docs/README.mdand whichever user guide covers the surface the change touches - For document-format or CLI-surface changes, read the deciding section of
docs/sandbox-spec.md/docs/cli-spec.mdand the Transitional-mode rules inCLAUDE.md
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 Changed 0c18436e76ee
- 5d ago First seen · 359 lines · 96 tokens per session scan A 566395e7447d
code-review is a skill published in the GitHub repository lensapp/lens-sandbox (10 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 2,874 once invoked, about $0.0005 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…