code-review

code-review is a skill for Claude Code, Codex from Alex8791-cyber/cognithor. It costs 13 tokens per session (499 once invoked), scanned A, original, Apache-2.0.

A structured code-review skill that examines a file or directory for security, performance, readability, and design problems.

In plain words
What is it for?
It is for reviewing source code, finding issues such as injection risks or duplicated work, and suggesting improvements.
Why use it?
It turns a general request for feedback into an organized review with findings grouped by severity and linked to code locations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing source code, finding issues such as injection risks or duplicated work, and suggesting improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alex8791-cyber/cognithor/custom
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 Alex8791-cyber/cognithor --skill custom
Clone the repo
git clone --depth 1 https://github.com/Alex8791-cyber/cognithor

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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alex8791-cyber/cognithor/custom/github.svg)](https://agentmods.dev/skills/alex8791-cyber/cognithor/custom)
Your own site
<a href="https://agentmods.dev/skills/alex8791-cyber/cognithor/custom"><img src="https://agentmods.dev/badge/skills/alex8791-cyber/cognithor/custom/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.

agentmods 80×15 button for code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alex8791-cyber/cognithor/custom"><img src="https://agentmods.dev/badge/skills/alex8791-cyber/cognithor/custom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00013 $0.00499
Opus 5 $0.00006 $0.00249
Sonnet 5 $0.00003 $0.00100
Haiku 4.5 $0.00001 $0.00050

Measured 6d ago against content hash 36e42adfa878, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 6d 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.

examples/custom_skill.md · 64 lines

What it actually says

Code Review

When to Apply

When the user asks for a code review, quality check, or wants feedback on their code. Typical triggers: "Review this file", "Check the code quality", "What can I improve in src/...".

Prerequisites

  • A file path or directory to review
  • Optional: specific focus areas (security, performance, readability)

Steps

  1. Identify target — Ask which file or directory to review if not specified.
  2. Read the code — Use read_file to load the target. For directories, use list_directory first, then read key files.
  3. Analyze — Use analyze_code for automated metrics (complexity, duplication, style). Note any issues.
  4. Review manually — Check for:
    • Security: injection, hardcoded credentials, path traversal
    • Performance: unnecessary loops, missing caching, N+1 queries
    • Readability: naming, function length, comments
    • Architecture: coupling, single responsibility, error handling
  5. Summarize — Present findings grouped by severity (critical, warning, suggestion) with line references.

Output Format

## Code Review: {filename}

### Critical
- Line 42: SQL injection via string concatenation

### Warnings
- Line 15-30: Function too long (87 lines), consider splitting
- Line 55: Bare except clause catches SystemExit

### Suggestions
- Line 8: Consider using `pathlib.Path` instead of `os.path`
- Missing type hints on public API functions

### Metrics
- Cyclomatic complexity: 12 (moderate)
- Lines of code: 234

Known Pitfalls

  • Do not modify files during review — this is a read-only operation.
  • For large directories, focus on the most important files first.
  • Be constructive — frame suggestions positively.

Quality Criteria

  • All critical issues identified
  • Specific line references provided
  • Actionable suggestions (not vague "improve this")
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. 6d ago First seen · 64 lines · 13 tokens per session scan A 36e42adfa878

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository Alex8791-cyber/cognithor (154 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 499 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 2026-09-03.