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 skills add Pawel-Kica/claude-code-100 --skill super-code-reviewgit clone --depth 1 https://github.com/Pawel-Kica/claude-code-100Wrote 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/pawel-kica/claude-code-100/super-code-review)<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>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 | $0.00020 | $0.00438 |
| Opus 5 | $0.00010 | $0.00219 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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.
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
-
Scope: current diff, staged and unstaged changes. Other possible scopes: PR, specific changeset.
-
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).
-
Merge. Dedupe overlapping findings across lenses, keep the sharpest wording. Group by severity, not by reviewer.
-
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 faithfulnessponytail-review: over-engineering and reinvented stdlibthermo-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.
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.
- 8d ago First seen · 42 lines · 20 tokens per session scan A dc13d9c24873
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
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…