scrutiny-validator

scrutiny-validator is a skill for Claude Code, Codex from Intelligent-Internet/zenith. It costs 45 tokens per session (1,450 once invoked), scanned A, original, Apache-2.0.

An adversarial validator for checking engineering implementations against assigned requirements and evidence. It reviews code, reports, commands, and validation records, then gives a verdict for each assigned target.

In plain words
What is it for?
Use it to audit engineering work, run required hard-gate commands, inspect source changes, and review whether evidence supports the reported results.
Why use it?
It helps catch unsupported claims, failed checks, and gaps between what was requested and what was implemented. It also separates code review from testing through a real user interface.

Skill for Claude CodeCodex

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

Good fit Use it to audit engineering work, run required hard-gate commands, inspect source…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/intelligent-internet/zenith/scrutiny-validator
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 Intelligent-Internet/zenith --skill scrutiny-validator
Clone the repo
git clone --depth 1 https://github.com/Intelligent-Internet/zenith

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 scrutiny-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/intelligent-internet/zenith/scrutiny-validator.svg)](https://agentmods.dev/skills/intelligent-internet/zenith/scrutiny-validator)
Your own site
<a href="https://agentmods.dev/skills/intelligent-internet/zenith/scrutiny-validator"><img src="https://agentmods.dev/badge/skills/intelligent-internet/zenith/scrutiny-validator.svg" alt="Measured on agentmods" 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 1,450 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 $0.01450
Opus 5 $0.00023 $0.00725
Sonnet 5 $0.00009 $0.00290
Haiku 4.5 $0.00005 $0.00145

Measured 7d ago against content hash 1a39bea34816, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scrutiny-validator 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 7d 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.

zenith/src/zenith_harness/bundled/skills/scrutiny-validator/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scrutiny Validator

Use this skill when the validation assignment asks for implementation scrutiny, hard-gate command review, evidence-integrity audit, or source review for engineering targets.

Scrutiny is not a substitute for real user/caller/operator surface validation. Use user-testing-validator or another surface-specific validator when the contract requires behavior through a real interface.

Inputs

Read:

  • Validation assignment, including exact target ids, assigned validation method, and any assignment-level setup or dependency notes.
  • Assigned assertions. Prefer compact fields/labels such as Surface, Needs, Behavior, Evidence, and optional Fail, Oracle, or Scope, but accept equivalent headings such as Statement for behavior, Evidence Floor for required evidence, and Non-Goals or Notes for boundaries.
  • AGENTS.md.
  • Latest worker report for each assigned target when present, plus relevant prior validator reports. Treat reports as claims, not proof.
  • Current product checkout files related to the targets. Treat diffs, claimed changes, and worker reports from prior attempts as useful leads when present, not as required inputs or proof.
  • Evidence artifacts, setup paths, oracle paths, source baselines, or regression ledgers cited by assignment, contract, prior attempts, or skill.

Procedure

  1. Establish scope
    • Identify exact target ids and the current product behavior, files, and evidence surfaces being scrutinized.
    • Parse every assigned assertion into behavior, surface, required evidence, prerequisites, oracle, failure conditions, and scope boundaries. Accept equivalent headings such as Statement, Evidence Floor, Non-Goals, and Notes when they provide the same meaning.
    • If behavior, surface, or required evidence cannot be determined from the assertion and validation assignment, mark the target unverifiable.
    • Map each target's Needs and Evidence requirements before reviewing implementation or evidence surfaces. Do not assume prerequisites, setup, fixtures, services, source baselines, or accepted decisions that are not present.
    • Map each target to implementation files and evidence-producing files.

Read the full file on GitHub · 146 lines

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. 7d ago First seen · 146 lines · 45 tokens per session scan A 1a39bea34816

Subscribe to this mod's changes

scrutiny-validator is a skill published in the GitHub repository Intelligent-Internet/zenith (290 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,450 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

review-prs

Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…

googleapis/mcp-toolbox · 162 tokens

discount-review

Inspect the discount policy fixture with a repeatable review checklist and helper script.

promptfoo/promptfoo · 18 tokens

code-review

Reviews code for bugs, security issues, and best practices.

promptfoo/promptfoo · 11 tokens

mantis-plan

Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or patching code.

google/mantis · 62 tokens

mantis-summarize

Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching…

google/mantis · 66 tokens

review

Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate. Produces review.md with decision points. Requires developer approval before $ship can proceed.

Snowflake-Labs/cocoplus · 50 tokens