code-reviewer

A code-review guide focused on security, system-level defects, and whether code follows its stated behavior. It requires each finding to include file-and-line evidence and a reproducible explanation.

In plain words
What is it for?
Reviewing pull requests and other code changes for bugs, security vulnerabilities, incorrect contracts, and problems specific to the technology stack. It does not modify code.
Why use it?
It helps reviewers focus on demonstrable problems instead of subjective style preferences or unsupported concerns.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/spumer/i-m-senior-developer/code-reviewer
Any agent
npx skills add spumer/i-m-senior-developer --skill code-reviewer
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code, Codex.

Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00162 $0.07160
Opus 5 $0.00081 $0.03580
Sonnet 5 $0.00032 $0.01432
Haiku 4.5 $0.00016 $0.00716

Measured 2d ago against content hash 8d63b56a060b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer 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.

plugins/sdlc/skills/code-reviewer/SKILL.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code-Reviewer — system-level + security

Reviews code changes for system-level issues, security vulnerabilities, and FPF violations in changes not authored by the reviewer. Output is a structured review report with file:line evidence; this skill never modifies code.

Always-active rule: When reviewing any code, load references/security.md regardless of stack or apparent diff scope. This is non-negotiable.

Principles

  1. System issues over taste. "I would name this differently" is not a review item. "This name says what it does, but the function does something else" is. Flag objective defects — correctness, safety, contract adherence. Skip subjective preferences entirely, or relegate to a ## Minor section the implementer can choose to ignore. One naming class is exempt from this principle: a vocabulary leak across a context boundary (layer, module, service) — it has a reproducible criterion (the substitution test), not taste; see System-issues focus.

  2. Evidence per finding (FPF A.10). Every item requires file:line + reproduction or proof: a test that fails, a query that 500s, a code path that silently swallows an exception. A finding without evidence is an opinion. Opinions do not belong in a review report. Before writing a finding, identify its concrete evidence; if none can be cited, the finding is either a style note or a design concern — label it accordingly. This cuts both ways: a claim the reviewer receives — an incoming finding, a "tests pass" self-report, or a legacy/unused-by-name assumption — is equally a hypothesis until its load-bearing line is checked against the source (Gotcha 8).

  3. Security always. Load references/security.md even if the diff "looks innocent" — a configuration change, a rename, a refactor. Secrets and auth bugs slip in via innocuous-looking changes. The ## Security section appears in every report, even when the result is "no security issues found in scope." The empty section is a force-function; its presence proves the check ran.

Read the full file on GitHub · 343 lines

Files

What ships with it

4 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.

Changes

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.

  1. 2d ago First seen · 343 lines · 162 tokens per session scan A 8d63b56a060b

Subscribe to this mod's changes

code-reviewer is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. It adds 162 tokens to every session and 7,160 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens