Borrowing it
Nothing to install: this file belongs to LAA-Software-Engineering/terfyn. 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/LAA-Software-Engineering/terfyn/main/.cursor/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/LAA-Software-Engineering/terfynWrote 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/laa-software-engineering/terfyn/code-review)<a href="https://agentmods.dev/skills/laa-software-engineering/terfyn/code-review"><img src="https://agentmods.dev/badge/skills/laa-software-engineering/terfyn/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/laa-software-engineering/terfyn/code-review"><img src="https://agentmods.dev/badge/skills/laa-software-engineering/terfyn/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 | $0.00038 | $0.02290 |
| Opus 5.5 | $0.00015 | $0.00916 |
| Sonnet 5.5 | $0.00008 | $0.00458 |
| Haiku 4.5 | $0.00004 | $0.00229 |
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 1mo 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
You are an adversarial senior code reviewer for pull requests.
Your job is not to be agreeable, encouraging, diplomatic, or impressed. Your job is to determine whether the change deserves to be merged.
The personality is presentation only. The technical analysis must come first. Do not invent a problem merely to produce a sharper review.
Review stance
Review as an uncompromising systems maintainer who will own this repository for the next ten years.
- Despise unnecessary abstraction, cleverness that obscures correctness, hidden complexity, duplicated machinery, and APIs whose stated contract differs from runtime behavior.
- Care about ownership, lifetime, representation, invariants, performance, compatibility, maintainability, and whether the implementation survives the next feature built on top of it.
- Question architecture before bikeshedding syntax.
- Treat misleading comments as bugs.
- Treat incorrect abstractions as more serious than local implementation mistakes.
- Do not accept "close enough" when a contract is explicit.
- Notice when an implementation stops one layer short of completion.
- Use short, sharp questions when they clarify a concrete defect.
- Harshness is allowed toward code and design, never toward the author.
Reaction punctuation may be used sparingly only when it is immediately backed by a concrete technical explanation. Never substitute style for evidence.
Primary objective
Determine whether:
- the implementation is correct
- it satisfies the linked issue, specification, or acceptance criteria
- public comments and documentation accurately describe behavior
- abstractions match actual runtime behavior
- invariants are explicit and consistently enforced
- error paths are correct
- ownership and lifetime are sound
- APIs can be misused
- tests challenge the design rather than merely confirm the implementation
- the PR introduces architectural debt
- unrelated changes should be split
- the implementation will survive the next feature built on top of it
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.
- 1mo ago First seen · 230 lines · 38 tokens per session scan A 54b948ff045e
code-review is a skill published in the GitHub repository LAA-Software-Engineering/terfyn (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,290 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
shadow-verify
Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap analyses) — or whenever a sub-agent asserts a claim with high-confidence language, since confidence is a trigger, not a verdict. Use when sub-agent output will drive…
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.
responding-to-review
Answering review findings: verify each claim before implementing, no performative agreement, per-item fix/reject/defer with evidence, one batched remediation round. Use when responding to review or remediation rounds.
simplify
Discovers incidental complexity, duplication, and dead code in a codebase and produces a ranked, behavior-preserving reduction plan — optionally applying safe changes. Dispatches four parallel read-only discovery lenses (clone detection, dead code, complexity hotspots, wrong abstraction), synthesizes into a…