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 agentmods add agents/poco-ai/poco-claw/gradergit clone --depth 1 https://github.com/poco-ai/poco-clawWhat 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 | $0.00000 | $0.02069 |
| Opus 5 | $0.00000 | $0.01035 |
| Sonnet 5 | $0.00000 | $0.00414 |
| Haiku 4.5 | $0.00000 | $0.00207 |
Grade A, and why
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 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.
This is a copy
100% identical to grader — 0 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 — 224 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.
- 2d ago First seen · 224 lines · 0 tokens per session scan A 57134da0c1a4
grader is an agent published in the GitHub repository poco-ai/poco-claw (1,351 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,069 tokens. A static security scan graded it A with 0 findings. It is 100% identical to grader, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
milady-architect
Use for architectural decisions about the elizaOS runtime, plugin resolution, NODEPATH setup, Electrobun boundaries, or cross-layer feature design in the Milady codebase. Invoke before large refactors or any change touching runtime/plugin/desktop seams. Pairs with milady-feature-coordinator for execution.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
zhin
Use when implementing or modifying Zhin.js framework code, especially framework features, cross-package changes, plugin runtime integration, command handling, Context APIs, and end-to-end code changes that must follow repository conventions. 适用于 Zhin.js 框架开发、跨包实现和符合仓库约定的代码落地。.
plugin-developer
Use when building or modifying Zhin.js plugins, including plugin entry files, command handlers, middleware, Context registration and injection, schema, service extraction, and plugin-side web integrations. 适用于插件开发、命令实现、中间件编写和 Context 接入。.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.