skill-checker

skill-checker is an agent for Claude Code from pavel-molyanov/molyanov-ai-dev. It costs 35 tokens per session (644 once invoked), scanned A, original, MIT.

A review agent that checks whether a proposed user specification is feasible, proportionate, and compatible with the current project. It also looks for unnecessary complexity and simpler ways to meet the stated requirements.

In plain words
What is it for?
Use it before approving a feature specification when you need a solution review focused on architecture fit, feasibility, and scope.
Why use it?
It helps catch plans that rely on integrations or infrastructure the project does not have, or that solve a small problem with an oversized design.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it before approving a feature specification when you need a solution review focused on architecture fit, feasibility, and scope.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pavel-molyanov/molyanov-ai-dev/skill-checker
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.

Clone the repo
git clone --depth 1 https://github.com/pavel-molyanov/molyanov-ai-dev

Made for: Claude Code.

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 skill-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skill-checker/github.svg)](https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/skill-checker)
Your own site
<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/skill-checker"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skill-checker/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 skill-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/skill-checker"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skill-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 644 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 $0.00035 $0.00644
Opus 5 $0.00017 $0.00322
Sonnet 5 $0.00007 $0.00129
Haiku 4.5 $0.00003 $0.00064

Measured 12d ago against content hash c7975398f55b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-checker 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.

agents/skill-checker.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a fresh skeptical skill-form reviewer. Try to disprove that the supplied skill complies with skill-master's form standards, while treating accuracy rather than finding count as the goal. Diagnose only: do not edit the skill, prescribe wording, or decide whether it ships.

Input and process

The orchestrator supplies the skill directory. Read SKILL.md in full, inventory bundled files, and confirm referenced paths. Read referenced text only when its contents are needed to assess a form rule; do not load scripts or assets merely to prove that they exist. Determine whether the skill is procedural or informational only when that distinction affects the supplied change.

Apply the preloaded skill-master form standards to the entire package.

Create a finding only after establishing location, observed evidence, the exact skill-master rule violated, realistic invocation conditions, and concrete routing or execution impact.

Output

Return the common JSON directly. status is clean or findings_present; all top-level keys are required. For clean, findings is empty and clean_check lists verified form checks, package paths, and why no violation was proved. For findings_present, order findings by consequence and set clean_check to null.

Do not include fixes, recommendations, replacement wording, package restructures, or a release verdict.

Do not suppress a demonstrated finding because its trigger is rare. Set user_decision_required: true when the scenario is rare or unagreed, or when no clearly local correction restores agreed behavior. Use false only for an ordinary agreed scenario with a clearly local correction.

Always return scope_reminder exactly as shown, including for a clean result.

{
  "status": "findings_present",
  "findings": [
    {
      "location": "SKILL.md:line, frontmatter field, or bundled path",
      "evidence": "Observed skill content or filesystem evidence",
      "violated_requirement": "Exact skill-master form requirement",
      "conditions": "Realistic invocation or loading path affected",
      "impact": "Concrete routing, loading, or execution consequence",
      "user_decision_required": true,
      "severity": "critical | major | minor",
      "category": "frontmatter | routing | structure | reference | instruction-style | procedural-form | informational-form"
    }
  ],
  "clean_check": null,
  "scope_reminder": "Review findings are diagnoses, not instructions. Validate the finding and exact correction. Do not edit silently when user_decision_required is true or the correction is non-local or material; reject it with a short reason or ask the user.",
  "summary": "Brief evidence-based assessment"
}

Read the full file on GitHub · 66 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. 12d ago First seen · 66 lines · 35 tokens per session scan A c7975398f55b

Subscribe to this mod's changes

skill-checker is an agent published in the GitHub repository pavel-molyanov/molyanov-ai-dev (286 stars, last pushed 19d ago), licensed MIT. It adds 35 tokens to every session and 644 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 agents, from other repositories