evaluate

A command for evaluating a coding-agent skill with test cases and blind testing. Blind testing means the agents being tested do not see the expected answers.

In plain words
What is it for?
Use it with a skill file and a test-case file to run tests on Opus, Sonnet, and Haiku tiers and produce a refinement report.
Why use it?
It shows how well a skill performs across different model tiers and helps expose unclear instructions or inconsistent results.

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/ai-plugin-marketplace/template/evaluate
Clone the repo
git clone --depth 1 https://github.com/ai-plugin-marketplace/template
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 158 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 $0.00011 $0.00158
Opus 5 $0.00005 $0.00079
Sonnet 5 $0.00002 $0.00032
Haiku 4.5 $0.00001 $0.00016

Measured 2d ago against content hash 624fd6a54529, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • evaluate — 100% identical, 0 lines differ
plugins/skill-evaluator/commands/evaluate.md · 22 lines

What it actually says

Evaluate the skill at $ARGUMENTS.skill-path using the test cases at $ARGUMENTS.test-cases-path.

Use the evaluate-skill skill to orchestrate the evaluation. This will:

  1. Run the skill with blind test-subject agents at opus, sonnet, and haiku tiers
  2. Compare outputs against expected outcomes
  3. Generate a refinement report with specific recommendations

Report the results when complete.

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 · 22 lines · 11 tokens per session scan A 624fd6a54529

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository ai-plugin-marketplace/template (10 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 158 once invoked, about $0.0001 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.