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.
npx skills add emaraschio/cursor-commands --skill prompt-eval-debuggit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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.
[](https://agentmods.dev/skills/emaraschio/cursor-commands/prompt-eval-debug)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/prompt-eval-debug"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/prompt-eval-debug/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.
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/prompt-eval-debug"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/prompt-eval-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.01161 |
| Opus 5.5 | $0.00029 | $0.00464 |
| Sonnet 5.5 | $0.00015 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
prompt-eval-debug 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt eval debug
Role
You act as a prompt debugger for an arbitrary prompt the user is iterating on. You help them improve it by designing a tiny eval suite, classifying failures, and suggesting the smallest next change, not a blind full rewrite. You do not claim this repository's CI scored their ad-hoc suite.
When to use
Use when a prompt or skill underperforms and the user might otherwise rewrite it on vibes. For shipped commands in this catalog, stable cases eventually belong in skill-contracts/<name>/eval/cases.md per EVAL_GUIDE.md. For delegation design before autonomous work, use define-agent-goal. For code/runtime bugs, use debug-issue.
Workflow
Run phases in order.
Phase 0: Intake
- Require Prompt (paste the prompt under test) and Task (what the AI should do when given that prompt).
- If either is missing, ask one focused question for each gap before proceeding.
- Produce a one-paragraph summary of what the prompt is trying to accomplish.
Phase 1: Tiny eval suite
Produce exactly five cases in a table with columns: ID, Type, Input / scenario, Expected behavior, Notes.
| ID | Type | Requirement |
|---|---|---|
| C0 | control | Should always pass when the prompt is healthy |
| E1 to E3 | edge | Scenarios where the prompt could fail; use prior failure modes if the user supplied them |
| B1 | capability-boundary | Agent should escalate, ask for help, or refuse (not hallucinate success) |
Cases must use concrete inputs and expected behaviors, not vague "should work."
Phase 2: Run guidance
Tell the user to run each case against the current prompt (manual chat, script, or their harness). Do not execute the target prompt as production traffic unless the user explicitly asks you to run a case. Do not claim automated pass/fail scores unless the user reports results.
Phase 3: Diagnosis
For each case (or for failures the user reports), classify the root cause as exactly one primary type:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 97 lines · 73 tokens per session scan A 8cac7b067142
prompt-eval-debug is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,161 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
mobile-emulator-test
QA a native Android or Expo dev-client build end to end on the emulator, checking UI, Supabase, and Sentry for each CRUD step. Use for "test on emulator", "QA Android build", "verify native build", "white screen", "cache rehydration", or "adb reverse".
audit-accessibility
WCAG 2.2 audit via playwright-cli: crawl every page, inject axe-core, test keyboard nav, contrast, ARIA labels, heading order. Use when "audit accessibility", "check a11y", "WCAG audit", "check keyboard nav", or "test screen reader".
deploy-verify
Post-deploy smoke test across browser, Sentry, Supabase, Langfuse, and the public web. Use when "verify deploy", "smoke test production", "post-release check", or "ship or rollback". Deploy plus watch → workflow-ship-and-observe.
audit-realworld
Read-only conformance audit of a full-stack app against RealWorld ("Conduit"): API spec, shared E2E suite, closest-stack reference. Use when "audit against RealWorld", "Conduit conformance", or "is my full-stack app complete?".
enhance-web-forms
Build or upgrade web forms: accessible structure, schema-driven validation, client↔server parity. Use when "improve this form", "form validation", "accessible form", "multi-step form", "form error handling", or "the form UX is bad".
iterate-agent-harness
Turn an agent failure (premature stop, false completion, gamed check, missed file) into a rule, hook, or CI guard with a regression test. Use when "the agent stopped early again", "it gamed the test", or "add a guard so this doesn't recur".