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 rp1-run/rp1 --skill prompt-eval-buildergit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/prompt-eval-builder)<a href="https://agentmods.dev/skills/rp1-run/rp1/prompt-eval-builder"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/prompt-eval-builder/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/rp1-run/rp1/prompt-eval-builder"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/prompt-eval-builder.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 | $0.00030 | $0.00582 |
| Opus 5 | $0.00015 | $0.00291 |
| Sonnet 5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
prompt-eval-builder 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 3d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Eval Builder
Domain knowledge for building evaluation artifacts from prompt specifications. Provides extraction patterns, output templates, validation logic, and invocation prompt generation rules.
When to Use
- Generating promptfoo eval configs from command/agent prompts
- Extracting testable assertions from instruction text (primarily LLM rubrics)
- Creating test invocation prompts (user inputs that test the command)
- Validating generated YAML output
Assertion Types
LLM Rubrics (Default): Generated for most behavioral requirements. Rubrics contain REQUIRED/PROHIBITED/EDGE CASES sections and evaluate behavior holistically by checking output text AND Metadata JSON.
Programmatic Assertions (Complex Cases): Generated when requirements need exact counting, strict sequencing, or complex conditional logic that cannot be expressed in natural language rubrics. Uses type: javascript with file:// references to shared assertion functions.
Skill Files
| File | Purpose | When to Load |
|---|---|---|
| PATTERNS.md | Extraction categories, tool mappings, selection rules, invocation generation | Always - core knowledge |
| TEMPLATES.md | promptfoo YAML output templates, assertion formats | When generating YAML output |
| VALIDATION.md | YAML validation loop, error handling | When validating/writing output |
Loading Instructions
Agents using this skill:
- Read SKILL.md for overview
- Read PATTERNS.md for extraction/invocation rules (always needed)
- Read TEMPLATES.md for output format (for extraction agent)
- Use
scripts/validate-yaml.tsfor YAML validation
Scripts
| Script | Purpose | Usage |
|---|---|---|
scripts/validate-yaml.ts |
Validate YAML syntax | bun {skill_path}/scripts/validate-yaml.ts {output_file} |
Output format: { "valid": true } or { "valid": false, "error": "message" }
Workflow Overview
Extraction Flow
Prompt Text -> Pattern Analysis -> Requirement Categorization -> LLM Rubric Generation -> YAML Validation
\-> Programmatic Assertion (if complex)
What ships with it
4 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.
- 3d ago First seen · 72 lines · 30 tokens per session scan A b9ca983fd48d
prompt-eval-builder is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 3d ago), licensed Apache-2.0. It adds 30 tokens to every session and 582 once invoked, about $0.0002 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 2026-09-07.
Other skills, from other repositories
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
test-generator
A test-writing helper that creates unit or integration tests from the code's actual behavior and contracts. Unit tests check small pieces of code, while integration tests check how real components work together.
qa
Use when auditing test quality in any codebase — run the real suite, map coverage topology, rank untested behaviors by risk. Assess by default, write tests on request; tests are a spec, and the question is what change no test would catch.
acceptance-test-authoring
Use when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an acceptance stack, or implementing OpenSpec tasks that involve acceptance tests.
gherkin-authoring
Use when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data Tables, tags, or Gherkin embedded in Markdown.
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.