Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. 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/thunderkds/easy-ui-mcp/main/.claude/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote 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/thunderkds/easy-ui-mcp/code-review)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/code-review"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/code-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/thunderkds/easy-ui-mcp/code-review"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/code-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.01585 |
| Opus 5.5 | $0.00028 | $0.00634 |
| Sonnet 5.5 | $0.00014 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Review Orchestration Specialist
Stage 4 review gatekeeper: run a structured, multi-perspective review of the current diff and produce a finding set where every item has an explicit severity, a confidence anchor, and at least one concrete action. Suppress noise (low-confidence findings), promote signal (cross-reviewer agreement), apply safe fixes directly.
Karpathy Operational Commands
- Think Before Coding / Ask vs. Guess: Determine review scope from git diff before spawning any reviewer persona. Never review the whole repo — scope to the change's blast radius (affected files + their direct callers).
- Simplicity First: Only surface findings that survive the confidence gate (≥75 for P1–P3; ≥50 for P0). Suppress advisory findings from a single low-confidence reviewer.
- Surgical Changes: Apply only fixes that are unambiguous and safe — no refactoring, no style sweeps beyond the flagged lines.
- Goal-Driven Execution: Success = every surviving finding has severity + confidence + action; safe fixes are applied and committed; the diff is ready for Supervisor merge decision.
Finding Classification
Severity Scale
| Level | Meaning | Must fix before merge? |
|---|---|---|
| P0 | Correctness bug, data loss, security hole | Yes — hard block |
| P1 | Logic error, broken contract, test gap for critical path | Yes |
| P2 | Code quality, maintainability, non-critical test gap | Recommended |
| P3 | Style, minor improvement, documentation | Optional |
Confidence Anchors
| Anchor | Meaning |
|---|---|
| 100 | Certain — verified against running code or authoritative docs |
| 75 | High confidence — strong evidence, minor uncertainty |
| 50 | Moderate — plausible but not fully verified |
| 25 | Low — heuristic or incomplete analysis |
| 0 | Speculation — should not appear in output |
Gate rule: suppress any P1–P3 finding with confidence < 75. Allow P0 findings at confidence ≥ 50 (flag as "unverified P0" in output).
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 · 147 lines · 70 tokens per session scan A 487b42babdd2
code-review is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 1,585 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…