scrutinize

scrutinize is a skill for Claude Code from Alexander-Tyagunov/magician. It costs 45 tokens per session (202 once invoked), scanned A, original, MIT.

A code-review and repair process that runs separate checks for correctness, security, and simplicity, combines the findings, and fixes critical or high-priority problems.

In plain words
What is it for?
Use it when reviewing a diff or pull request before shipping, especially when you want review followed by targeted remediation.
Why use it?
It brings several review perspectives together and can address the most serious findings before release.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the magician plugin — 26 skills, 4 agents, 10 hooks shipped together

Good fit Use it when reviewing a diff or pull request before shipping, especially when you want review followed by targeted remediation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexander-tyagunov/magician/scrutinize
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 Alexander-Tyagunov/magician --skill scrutinize
Clone the repo
git clone --depth 1 https://github.com/Alexander-Tyagunov/magician

Made for: Claude Code.

Or install magician, the plugin that ships this one along with the rest of its 26 skills, 4 agents, 10 hooks.

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 scrutinize

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexander-tyagunov/magician/scrutinize/github.svg)](https://agentmods.dev/skills/alexander-tyagunov/magician/scrutinize)
Your own site
<a href="https://agentmods.dev/skills/alexander-tyagunov/magician/scrutinize"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/scrutinize/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 scrutinize

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexander-tyagunov/magician/scrutinize"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/scrutinize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 202 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 $0.00045 $0.00202
Opus 5 $0.00023 $0.00101
Sonnet 5 $0.00009 $0.00040
Haiku 4.5 $0.00005 $0.00020

Measured 12d ago against content hash 013e6b54e91a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

scrutinize 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 12d 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.

.codex-plugin/skills/scrutinize/SKILL.md · 11 lines

What it actually says

$scrutinize — Codex Adapter

Read ../../references/codex-adapter.md, then read ../../../skills/scrutinize/SKILL.md and follow the source skill through that Codex adapter. Keep the source skill's gates, safety checks, and completion criteria.

Dispatch correctness, security, and simplification as generic Codex agents only when collaboration tools are available. Every prompt must be self-contained (Goal, Scope, diff/intent inputs, constraints, evidence, Return format); never request magician:* or other Claude profiles. Store intermediate review patches/reports in a temporary directory so the review phase remains read-only. Apply remediation to repository files only after the source remediation gate, and never commit without explicit authorization.

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. 12d ago First seen · 11 lines · 45 tokens per session scan A 013e6b54e91a

Subscribe to this mod's changes

scrutinize is a skill published in the GitHub repository Alexander-Tyagunov/magician (14 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 202 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

reviewing

Claude-on-Claude code review protocol — reviews implementation against spec requirements and code quality standards.

LucasDuys/forge · 19 tokens

loop-verifier

The checker half of a maker/checker loop. Independently reviews a proposed fix before it becomes a PR. Has authority to REJECT. Never makes changes itself.

SUDARSHANCHAUDHARI/MyLoop · 37 tokens

g-review

Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.

onlygian/G-Forge · 46 tokens

g-refactor

Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.

onlygian/G-Forge · 0 tokens

g-audit

Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.

onlygian/G-Forge · 52 tokens

g-blast-radius

Analyse the blast radius of a planned change. Inputs a file path, feature name, or list of paths from a plan. Outputs the set of dependent files (forward and reverse references), a per-file volatility score (commit frequency proxy), and a total blast-radius rating (low / moderate / wide). Read-only.

onlygian/G-Forge · 68 tokens