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-evolutiongit 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-evolution)<a href="https://agentmods.dev/skills/miaodx/roboclaws/eval-evolution"><img src="https://agentmods.dev/badge/skills/miaodx/roboclaws/eval-evolution/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/miaodx/roboclaws/eval-evolution"><img src="https://agentmods.dev/badge/skills/miaodx/roboclaws/eval-evolution.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 | $0.00028 | $0.00733 |
| Opus 5.5 | $0.00011 | $0.00293 |
| Sonnet 5.5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
eval-evolution 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Evolution
Use this Skill for maintainer-owned optimization campaigns driven by frozen eval
evidence. roboclaws.evals remains the control plane. The optimizer and robot
trials are distinct OpenAI Agents SDK agents; a provider profile selects their
models and never changes the agent engine.
Prepare
Freeze an eval_evolution_campaign_v1 JSON manifest before the first optimizer
call. Bind one target kind and target, the baseline commit and target digest,
mutable paths, optimizer and robot provider/model identities, paired training
suites, the orchestrator-only sealed confirmation reference, quality and
minimum-improvement policy, runtime identity, and explicit turn/trial/token/
cost/time/retry ceilings.
The budget block also declares positive optimizer_call_tokens,
optimizer_call_cost_usd, robot_attempt_tokens, and
robot_attempt_cost_usd reservations. Each reservation is a frozen maximum for
one optimizer run or one robot attempt, not a post-hoc usage target.
Skill campaigns target exactly one skills/<name>/SKILL.md. Keep
static-full as the baseline. no-skill is a non-promotable negative control.
Do not mix Skill and MCP changes.
Run
Inspect the blocked preflight without provider execution:
just agent::eval evolve campaign=<campaign.json>
Run the frozen campaign only after provider/runtime readiness is established:
just agent::eval evolve campaign=<campaign.json> live_execution=run
The optimizer can only read the declared target, read sanitized feedback, and submit one hypothesis plus patch. It has no shell, filesystem, git, network, eval-launch, commit, or publication tool. Host-owned validation creates one content-addressed full baseline snapshot and runs deterministic gates before paired robot trials.
Review
Reject missing or mismatched identity, incomplete paired evidence, privacy or
checker failures, trajectory/terminal violations, quality regressions, neutral
rewrites, and no-skill. Efficiency ranks only candidates that meet the frozen
quality and minimum-improvement rule. At most one training winner reaches one
sealed confirmation. Its evidence never returns to the optimizer.
What ships with it
1 file 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 · 87 lines · 28 tokens per session scan A a976866b6b44
eval-evolution is a skill published in the GitHub repository MiaoDX/roboclaws (6 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 733 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
MeiGen
Compose MeiGen image/video and five dedicated image tools inside an existing workflow, or opt into creative planning. Preserves caller prompts, parameters, approved count and budget; includes discovery and recoverable task handles.
MeiGen Visual Creative Expert
Optional visual planning assistant. Use when the user asks MeiGen to develop a creative idea, explore visual directions, improve a prompt, or build a mood board. An existing upstream script, prompt, model choice or generation plan can call MeiGen tools directly without activating this creative workflow.
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
Social Thumbnail Workflow
A workflow for creating vertical images for short-video platforms and mobile social feeds, where content is usually viewed in a 9:16 portrait layout.
kaggle
Unified Kaggle skill. Use when the user explicitly mentions Kaggle, kaggle.com, a Kaggle URL, Kaggle competitions, Kaggle datasets/models/notebooks, Kaggle forums/discussions/writeups, Kaggle benchmarks, hackathons hosted on Kaggle, Kaggle badges, or Kaggle account setup. Do not use for generic ML, GPU/TPU, notebook…
you-web
Search the live web and read full pages with You.com. Use whenever a task needs information newer than training data or from outside the codebase: current library docs and API references, changelogs and release notes, breaking changes, error messages, package versions, pricing, news, or any claim to verify with cited…