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 MiaoDX/roboclaws --skill eval-harnessgit clone --depth 1 https://github.com/MiaoDX/roboclawsWrote 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/miaodx/roboclaws/eval-harness)<a href="https://agentmods.dev/skills/miaodx/roboclaws/eval-harness"><img src="https://agentmods.dev/badge/skills/miaodx/roboclaws/eval-harness.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01471 |
| Opus 5 | $0.00016 | $0.00736 |
| Sonnet 5 | $0.00007 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
eval-harness 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 6d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Harness
Use this skill when a Roboclaws plan, diff, PR, or agent-facing change needs one maintainer proof surface. The skill answers:
- which deterministic gates, product runs, eval suites, and live-agent evals are relevant;
- why each row was selected, skipped, run, failed, or blocked;
- where the resulting reports and regression-promotion evidence live.
It is an orchestration skill, not a robot behavior skill. Keep household-world
task strategy in household-world; keep reusable robot capability semantics
in MCP tools and capability profiles.
Use Just only as the human-facing facade shown below. Frozen rows execute their
package owners directly: eval rows use python -m roboclaws.evals.cli, and
product rows use python -m roboclaws.cli.main run surface. Keep the subprocess
boundary for row timeout and isolation; do not route an executing row back
through Just or add a second command registry. The eval CLI grammar is an
optional documented kebab-case tool name followed by key=value arguments.
Commands
Recommend rows without running them:
just agent::eval recommend plan=docs/plans/example.md budget=focused
Execute relevant rows for a plan or diff:
just agent::eval execute plan=docs/plans/example.md budget=focused
just agent::eval execute since=origin/main budget=focused
just agent::eval execute profile=baseline-core budget=focused max_parallel=4
Pass scene=<source>/<index>,... to expand rows whose catalog uses scene_scope=selected; the current scene-portable rows are the MapBuild product rows. Case identity, dependencies, commands, and result schema are resolved before local execution. Scheduling respects shared backend locks and writes one result per frozen benchmark case.
Refresh the current baseline at the appropriate cost tier:
just agent::eval execute profile=baseline-core budget=focused
just agent::eval execute profile=baseline-live-default budget=focused
just agent::eval execute profile=baseline-refresh budget=focused
What ships with it
2 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.
- 6d ago First seen · 147 lines · 33 tokens per session scan A d68c3062a52e
eval-harness is a skill published in the GitHub repository MiaoDX/roboclaws (6 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,471 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 2026-08-31.
Other skills, from other repositories
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
afrexai-react-production
Complete methodology for building production-grade React applications with architecture decisions, component design, state management, performance optimization, testing, and deployment.
Vibe Coding Mastery
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
api-tester
API testing expert for curl, REST, GraphQL, authentication, and debugging.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.