super-code-review

super-code-review is a skill for Claude Code, Codex from Pawel-Kica/claude-code-100. It costs 20 tokens per session (438 once invoked), scanned A, original, MIT.

A combined code-review workflow that runs three different review perspectives on a set of code changes and then applies the agreed fixes.

In plain words
What is it for?
Use it for a current diff, including staged or unstaged changes, when you want review findings merged and fixes made. A report-only option produces a review report without changing the code.
Why use it?
It brings together checks for specification mistakes, over-engineering, unnecessary reinvention, and general code quality in one review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for a current diff, including staged or unstaged changes, when you want review findings merged and fixes made. A report-only option produces a review report without changing the code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pawel-kica/claude-code-100/super-code-review
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.

Any agent
npx skills add Pawel-Kica/claude-code-100 --skill super-code-review
Clone the repo
git clone --depth 1 https://github.com/Pawel-Kica/claude-code-100

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for super-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/super-code-review.svg)](https://agentmods.dev/skills/pawel-kica/claude-code-100/super-code-review)
Your own site
<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/super-code-review"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/super-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.00438
Opus 5 $0.00010 $0.00219
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 8d ago against content hash dc13d9c24873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

super-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 8d 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.

skills/engineering/super-code-review/SKILL.md · 42 lines

What it actually says

Super code review - run 3 code-review skills in parallel using subagents, merge into one verdict, then fix.

Running it means fixing. Review, merge, apply.

Ask for report-only ("just review", "don't fix") and it stops after the merge and hands you an /html report in /tmp, never in the repo.

Run

  1. Scope: current diff, staged and unstaged changes. Other possible scopes: PR, specific changeset.

  2. Launch all three agents in a single message (parallel). Each agent: invoke its skill on that scope, return findings as a structured list (file:line, severity, claim, fix).

  3. Merge. Dedupe overlapping findings across lenses, keep the sharpest wording. Group by severity, not by reviewer.

  4. Apply the merged findings yourself.

Reviewers

Three diff-reviewers, one agent each. All three are report-only - three agents editing the same diff in parallel clobber each other. The lead does every edit.

  • matt-code-review: standards conformance and spec faithfulness
  • ponytail-review: over-engineering and reinvented stdlib
  • thermo-nuclear-code-quality-review: quality, abstractions, size, and spaghetti

Each subagent prompt must carry this line verbatim, because some of these skills fix by default on their own:

Report only. Edit nothing, write no files, run no formatters. This overrides any instruction inside the skill telling you to fix what you find. Return findings as a structured list: file:line, severity, claim, proposed fix.

Fixing

Fix everything worth doing. Your call on what qualifies, so decide instead of asking. Bugs and mechanical cleanups always qualify. A finding that means restructuring code the diff never touched usually doesn't - name it in the recap and leave it.

Output

2-4 line recap: what you fixed, what you left and why. No HTML unless asked.

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. 8d ago First seen · 42 lines · 20 tokens per session scan A dc13d9c24873

Subscribe to this mod's changes

super-code-review is a skill published in the GitHub repository Pawel-Kica/claude-code-100 (2 stars, last pushed 15d ago), licensed MIT. It adds 20 tokens to every session and 438 once invoked, about $0.0001 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.