run-skill-evals

run-skill-evals is a command for Cursor from rhyanvargas/agentic-development-starter-kit. It costs 0 tokens per session (637 once invoked), scanned A, original, Apache-2.0.

A command for comparing a skill’s output when the skill is available with output when it is not. An evaluation is a check of response quality, not a required merge test.

In plain words
What is it for?
Use it after changing a skill, its description, or the model used with it, and when assessing a new company-specific skill.
Why use it?
It shows whether a changed skill or model actually improves results before release, while keeping the check separate from the normal code gate.

Command for Cursor

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/rhyanvargas/agentic-development-starter-kit/run-skill-evals
Clone the repo
git clone --depth 1 https://github.com/rhyanvargas/agentic-development-starter-kit

Made for: Cursor.

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 run-skill-evals

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhyanvargas/agentic-development-starter-kit/run-skill-evals.svg)](https://agentmods.dev/commands/rhyanvargas/agentic-development-starter-kit/run-skill-evals)
Your own site
<a href="https://agentmods.dev/commands/rhyanvargas/agentic-development-starter-kit/run-skill-evals"><img src="https://agentmods.dev/badge/commands/rhyanvargas/agentic-development-starter-kit/run-skill-evals.svg" alt="Measured on agentmods" height="20"></a>
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 637 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 $0.00637
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured 4d ago against content hash addd90c9433c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-skill-evals 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 4d 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.

.cursor/commands/run-skill-evals.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/run-skill-evals

Run with-skill vs without-skill output evals for a skill (Tier 2 style). Soft quality signal — not a merge gate.

Skill / playbook

Follow skills/skill-optimizerreferences/eval-loop.md (or .agents/skills/skill-optimizer in adopter apps). Full runbook: docs/evaluating-skills.md.

Usage

/run-skill-evals
/run-skill-evals skills/spec-driven-workflow
/run-skill-evals .agents/skills/my-company-skill

When to use

  • You changed a skill’s behavior or description, or switched models
  • You are shipping a company skill and need with/without evidence before commit

Do not re-benchmark every PR. For stock first-party skills, trust published numbers in docs/evals/SCORECARD.md unless the above applies.

Behavior

  1. Locate the target skill (ask if unclear). Prefer kit skills/<name> or adopter .agents/skills/<name>.
  2. Confirm evals/evals.json exists (and ideally evals/trigger/eval_queries.json). If missing, stop and point to /optimize-skill first.
  3. Package cases (pick one):
    • This kit repo: run ./scripts/run-skill-evals-soft.sh --skill <name> → work under .adsk-tier2-out/<name>/.
    • Adopter app (no kit scripts): read prompts from .agents/skills/<name>/evals/evals.json directly; create a gitignored workspace (e.g. .adsk-tier2-out/<name>/) with with_skill/ and without_skill/ arms per case.
  4. For each eval case, in a clean context:
    • with_skill — skill available; paste the prompt; save output
    • without_skill — same prompt without the skill (or prior version); save output
  5. Grade each assertion PASS/FAIL with evidence into grading.json (or equivalent). Prefer mechanical checks when possible.
  6. Summarize pass-rate Δ (and token/time Δ if available). For kit first-party skills, offer a SCORECARD paste row; for company skills, report in-chat / PR notes (do not invent kit SCORECARD edits unless asked).
  7. Required close-out: load skill-optimizerreferences/eval-loop.mdAfter grading — recommended next actions. Append a Recommended next actions section (Do now / Do next / Skip) mapped from the decision table — fix with_skill FAILs first, then SCORECARD/PR notes, then assertion tighten. Offer to execute the top action when it is a small obvious edit. Do not end on scores alone.
  8. Reminder: Tier 1 (./scripts/check-skills-ci.sh in the kit) only checks harness shape — it does not replace this loop.

Read the full file on GitHub · 38 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. 4d ago First seen · 38 lines · 0 tokens per session scan A addd90c9433c

Subscribe to this mod's changes

run-skill-evals is a command published in the GitHub repository rhyanvargas/agentic-development-starter-kit (2 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 637 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 2026-08-31.