Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pitimon/8-habit-ai-dev/plugin install 8-habit-ai-devWrote 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/pitimon/8-habit-ai-dev/scrutinize)<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/scrutinize"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/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.
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/scrutinize"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/scrutinize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00117 | $0.03122 |
| Opus 5 | $0.00059 | $0.01561 |
| Sonnet 5 | $0.00023 | $0.00624 |
| Haiku 4.5 | $0.00012 | $0.00312 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrutinize (มองจากภายนอก แล้วไล่ทางจริง)
Habit: H5 — Seek First to Understand + H8 — Find Your Voice | Anti-pattern: Rubber-stamp "LGTM" reviews that only check what's already in the diff
Stand outside the change and ask whether it should exist at all, then verify it actually does what it claims end-to-end. Different from /review-ai: that skill checks security/quality/perf on the diff. This skill questions scope, traces the call graph, and surfaces whether a simpler alternative was missed.
Operating Stance
- Outsider. Forget who wrote it and why they think it's right. Read the artifact cold.
- End-to-end, not diff-local. The diff is the entry point, not the scope. Follow the call graph through real code paths.
- Actionable, concise, with rationale. Every finding states what to change, why, and what evidence led you there. No filler, no restating the diff back.
When to Use
- Before committing to an implementation approach (after
/designor/build-brief, before code is written). - Before merging a PR — as a second pass alongside
/review-ai. - When a plan or design doc feels "fine" but you want an independent check.
- When the user says "scrutinize", "sanity-check", "second opinion", "outsider review", "audit this approach".
When to Skip
- Auto-generated formatting changes (lint --fix, prettier) — nothing to question.
- Dependency version bumps with passing CI and no API surface change.
- Reverting a commit to its exact previous state.
- Single-line typo fixes.
Workflow — Run in Order, Do Not Skip Ahead
1. Intent — what is this actually trying to do?
- State the goal in one sentence, in your own words. If you cannot, the artifact is underspecified — say so and stop.
- Ask: is there a simpler, smaller, or more elegant way to achieve the same goal? Consider:
- Doing nothing (is the problem real / load-bearing?).
- Using something that already exists in the codebase instead of adding new surface.
- A smaller change that solves 90% of the goal with 10% of the risk.
- Solving it at a different layer (config vs code, framework vs app, build vs runtime).
- If a better alternative exists, name it explicitly with rationale. This is the most valuable thing you can output — surface it before the line-by-line review.
- When you reject an alternative (or judge the current approach a trap), first state its strongest case (steelman), then tag why even that best case fails — hidden cost / false economy / scaling failure / premature abstraction (commandment 14,
integrity-principles.md).
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.
- 9d ago First seen · 174 lines · 117 tokens per session scan A 62c72fbc9c3a
scrutinize is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 3,122 once invoked, about $0.0006 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
two-axis-review
Two-axis review: Standards vs Spec, unmerged.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…