aigent-scorer

aigent-scorer is a skill for Claude Code from wkusnierczyk/aigent. It costs 57 tokens per session (624 once invoked), scanned A, original, Apache-2.0.

A quality checker for agent skill definitions stored in SKILL.md files. It rates their structure and instructions against a defined best-practices checklist.

In plain words
What is it for?
Use it to score a skill from 0 to 100, inspect structural and quality results, or produce machine-readable output with the aigent command.
Why use it?
It reveals missing or invalid fields and unclear guidance before a skill is shared or used by an agent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the aigent plugin — 3 skills, 1 hook shipped together

Good fit Use it to score a skill from 0 to 100, inspect structural…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wkusnierczyk/aigent/aigent-scorer
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 wkusnierczyk/aigent --skill aigent-scorer
Clone the repo
git clone --depth 1 https://github.com/wkusnierczyk/aigent

Made for: Claude Code.

Or install aigent, the plugin that ships this one along with the rest of its 3 skills, 1 hook.

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 aigent-scorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/wkusnierczyk/aigent/aigent-scorer.svg)](https://agentmods.dev/skills/wkusnierczyk/aigent/aigent-scorer)
Your own site
<a href="https://agentmods.dev/skills/wkusnierczyk/aigent/aigent-scorer"><img src="https://agentmods.dev/badge/skills/wkusnierczyk/aigent/aigent-scorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00057 $0.00624
Opus 5 $0.00028 $0.00312
Sonnet 5 $0.00011 $0.00125
Haiku 4.5 $0.00006 $0.00062

Measured 6d ago against content hash 5d337e57461d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aigent-scorer 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.

skills/aigent-scorer/SKILL.md · 87 lines

What it actually says

Skill Scorer

Setup

Check if aigent is available:

command -v aigent

With aigent CLI

If aigent is on $PATH, use the CLI for authoritative scoring:

aigent score <skill-directory>

Output shows a 0-100 score with breakdown:

Score: 76/100

Structural (60/60):
  [PASS] SKILL.md exists and is parseable
  [PASS] Name format valid
  ...

Quality (16/40):
  [PASS] Third-person description
  [FAIL] Missing trigger phrase
  ...

Use --format json for machine-readable output.

Exit code 0 means perfect score (100/100). Non-zero means room for improvement.

Without aigent CLI

If aigent is not available, score manually using this checklist.

Structural checks (60 points)

All structural checks must pass to earn 60 points. Any failure zeroes the structural score.

  1. SKILL.md exists — file present with valid YAML frontmatter
  2. Name format — lowercase, hyphens, digits only; no consecutive hyphens; no leading/trailing hyphens; no reserved words; matches directory name; 64 chars max
  3. Description valid — non-empty, 1024 chars max, no XML tags
  4. Required fieldsname and description present and string-typed
  5. No unknown fields — only spec-defined keys in frontmatter
  6. Body size — body under 500 lines

Quality checks (40 points, 8 each)

Each passing check earns 8 points.

  1. Third-person description — no "I", "me", "my", "you", "your"
  2. Trigger phrase — description includes "Use when", "Use for", or similar
  3. Gerund name — first segment ends in "-ing" (e.g., "processing-pdfs")
  4. Specific name — not generic ("helper", "utils", "tools", etc.)
  5. Detailed description — at least 20 characters and 4 words

Scoring formula

total = structural_pass ? 60 : 0
total += quality_checks_passed * 8

Maximum score: 100 (60 structural + 40 quality).

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 · 87 lines · 57 tokens per session scan A 5d337e57461d

Subscribe to this mod's changes

aigent-scorer is a skill published in the GitHub repository wkusnierczyk/aigent (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 624 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens