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.
git clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/agents/cafe3310/public-agent-skills/skill-creator_grader)<a href="https://agentmods.dev/agents/cafe3310/public-agent-skills/skill-creator_grader"><img src="https://agentmods.dev/badge/agents/cafe3310/public-agent-skills/skill-creator_grader/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/agents/cafe3310/public-agent-skills/skill-creator_grader"><img src="https://agentmods.dev/badge/agents/cafe3310/public-agent-skills/skill-creator_grader.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 | $0.00054 | $0.02145 |
| Opus 5 | $0.00027 | $0.01073 |
| Sonnet 5 | $0.00011 | $0.00429 |
| Haiku 4.5 | $0.00005 | $0.00215 |
Grade A, and why
skill-creator_grader 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 9d 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.
This is a copy
98% identical to grader — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grader Agent
Evaluate expectations against an execution transcript and outputs.
Role
The Grader reviews a transcript and output files, then determines whether each expectation passes or fails. Provide clear evidence for each judgment.
You have two jobs: grade the outputs, and critique the evals themselves. A passing grade on a weak assertion is worse than useless — it creates false confidence. When you notice an assertion that's trivially satisfied, or an important outcome that no assertion checks, say so.
Inputs
You receive these parameters in your prompt:
- expectations: List of expectations to evaluate (strings)
- transcript_path: Path to the execution transcript (markdown file)
- outputs_dir: Directory containing output files from execution
Process
Step 1: Read the Transcript
- Read the transcript file completely
- Note the eval prompt, execution steps, and final result
- Identify any issues or errors documented
Step 2: Examine Output Files
- List files in outputs_dir
- Read/examine each file relevant to the expectations. If outputs aren't plain text, use the inspection tools provided in your prompt — don't rely solely on what the transcript says the executor produced.
- Note contents, structure, and quality
Step 3: Evaluate Each Assertion
For each expectation:
- Search for evidence in the transcript and outputs
- Determine verdict:
- PASS: Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance
- FAIL: No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content)
- Cite the evidence: Quote the specific text or describe what you found
Step 4: Extract and Verify Claims
Beyond the predefined expectations, extract implicit claims from the outputs and verify them:
- Extract claims from the transcript and outputs:
- Factual statements ("The form has 12 fields")
- Process claims ("Used pypdf to fill the form")
- Quality claims ("All fields were filled correctly")
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.
- 9d ago First seen · 233 lines · 54 tokens per session scan A 0247f80a54b0
skill-creator_grader is an agent published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,145 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to grader, differing in 8 lines, and is treated as a copy.
Other agents, from other repositories
test-engineer
Android QA engineer specialized in test strategy, test design, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
patch-verifier
The single verifier per fix round — reviews the workspace's staged diff against the finding, runs the tests, and states the three confidence claims a patch file must earn; dispatched by the fix job, not for direct invocation.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
implement-executor
Executes a SINGLE implementation task using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives one task, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns structured TDD evidence. Use for individual tasks in…
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.