eval-skill

A command that evaluates a coding skill file against six separate quality dimensions, using local JavaScript checks for some dimensions and language-model review for others.

In plain words
What is it for?
Use it to evaluate an SKILL.md file at gate, target, or full scope and receive dimension-based results.
Why use it?
It helps find weaknesses in a skill file before relying on it, while limiting the amount of model processing needed for simpler checks.

Command

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.

agentmods
npx agentmods add commands/evol-ai/skillcompass/eval-skill
Clone the repo
git clone --depth 1 https://github.com/Evol-ai/SkillCompass
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04709
Opus 5 $0.00000 $0.02354
Sonnet 5 $0.00000 $0.00942
Haiku 4.5 $0.00000 $0.00471

Measured 2d ago against content hash 9806ae0335dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-skill scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 2d 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.

commands/eval-skill.md ยท 417 lines

How it starts

The opening of the file, as written. The whole thing โ€” 417 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

/eval-skill โ€” Six-Dimension Evaluation

๐Ÿš€ Enhanced with Local Validators: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. Complex reasoning tasks (D4, D5, D6) continue to use LLM evaluation with local pre-analysis.

Prerequisites

  • Recommended model: Claude Opus 4.6 (claude-opus-4-6). The 6-dimension rubric requires complex multi-dimensional reasoning, nuanced security analysis, and consistent scoring across dimensions. Sonnet and Haiku may produce inconsistent dimension scores, miss subtle security findings in D3, and generate unreliable D5 comparative assessments. If not using an Opus-class model, treat results as approximate.

Arguments

  • <path> (required): Path to the SKILL.md file to evaluate.
  • --scope [gate|target|full] (optional, default: full): Evaluation scope.
    • gate: D1 + D3 only (~8K tokens). Outputs "partial": true.
    • target --dimension D{N}: specified dimension + D3 gate (~12K tokens). Outputs "partial": true.
    • full: all 6 dimensions (~40K tokens). Default behavior.
  • --dimension D{N} (optional): Used with --scope target to specify which dimension.
  • --format [json|md|all] (optional, default: json): Output format.
  • --feedback <path> (optional): Path to a feedback signal JSON file.
  • --ci (optional): CI-friendly mode. Suppresses interactive prompts, outputs JSON only, sets exit code (0=all PASS, 1=CAUTION, 2=FAIL).

Error Handling

  • File not found: Stop immediately. Output "Error: File not found: {path}" (translate at display time).
  • Not a SKILL.md: Warn "Warning: filename is not SKILL.md โ€” continuing with evaluation." if applicable.
  • YAML malformed: Warn "Warning: YAML frontmatter is malformed.", set D1 frontmatter_sub = 0, continue with remaining checks.

Steps

Step 1: Load Target

Parse arguments. Check current model โ€” if not an Opus-class model, output this warning (translate to the session locale at display time):

โš  Warning: Current model is {model_name}. For reliable 6D evaluation, Claude Opus 4.6 is recommended. Results may be less consistent with other models.

Read the full file on GitHub ยท 417 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. 2d ago First seen ยท 417 lines ยท 0 tokens per session scan A 9806ae0335dd

Subscribe to this mod's changes

eval-skill is a command published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,709 tokens. 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 commands, from other repositories