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 cobosteven/cobo-agent-wallet-manual --skill caw-evalgit clone --depth 1 https://github.com/cobosteven/cobo-agent-wallet-manualWrote 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/cobosteven/cobo-agent-wallet-manual/caw-eval)<a href="https://agentmods.dev/skills/cobosteven/cobo-agent-wallet-manual/caw-eval"><img src="https://agentmods.dev/badge/skills/cobosteven/cobo-agent-wallet-manual/caw-eval/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/cobosteven/cobo-agent-wallet-manual/caw-eval"><img src="https://agentmods.dev/badge/skills/cobosteven/cobo-agent-wallet-manual/caw-eval.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 | $0.00129 | $0.02648 |
| Opus 5.5 | $0.00052 | $0.01059 |
| Sonnet 5.5 | $0.00026 | $0.00530 |
| Haiku 4.5 | $0.00013 | $0.00265 |
Grade A, and why
caw-eval 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 2mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
27 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.
- QUICK_START.md 8.0 KB
- references/common-execution.md 6.6 KB
- references/dataset-management.md 7.2 KB
- references/dataset-review.md 9.9 KB
- references/issue-attribution.md 21 KB
- references/run-eval-cc.md 12 KB
- references/run-eval-openclaw.md 23 KB
- references/run-eval-recipe.md 11 KB
- references/scoring.md 13 KB
- references/server-setup.md 7.4 KB
- scripts/.env.example 874 B
- scripts/assertions.py 46 KB runs code
- scripts/bootstrap_cc_server.sh 1.7 KB runs code
- scripts/eval_utils.py 15 KB runs code
- scripts/fan_out_bootstrap.sh 2.4 KB runs code
- scripts/generate_dataset.py 47 KB runs code
- scripts/judge_cc.py 21 KB runs code
- scripts/pilot_recipe_eval.py 12 KB runs code
- scripts/run_eval_cc.py 80 KB runs code
- scripts/run_eval_openclaw.py 104 KB runs code
- scripts/runtime_compliance.py 8.4 KB runs code
- scripts/schemas.py 7.5 KB runs code
- scripts/score_traces.py 133 KB runs code
- scripts/spec_derivation.py 4.7 KB runs code
- scripts/sync_to_servers.sh 14 KB runs code
- scripts/upload_session.py 45 KB runs code
- scripts/validate_dataset.py 3.6 KB runs code
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.
- 2mo ago First seen · 155 lines · 129 tokens per session scan A d001a851526c
caw-eval is a skill published in the GitHub repository cobosteven/cobo-agent-wallet-manual (0 stars, last pushed 5mo ago), with no licence file. It adds 129 tokens to every session and 2,648 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
caw-eval compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| caw-evalcobosteven/cobo-agent-wallet-manual | Skill | 0 | 5mo ago | none | A | 129 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |