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 ZekaiShi/evo-subagent --skill evo-delegation-guidegit clone --depth 1 https://github.com/ZekaiShi/evo-subagentWrote 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/zekaishi/evo-subagent/evo-delegation-guide)<a href="https://agentmods.dev/skills/zekaishi/evo-subagent/evo-delegation-guide"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-delegation-guide/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/zekaishi/evo-subagent/evo-delegation-guide"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-delegation-guide.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 | $0.00041 | $0.00291 |
| Opus 5.5 | $0.00016 | $0.00116 |
| Sonnet 5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
evo-delegation-guide 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 today.
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.
What it actually says
Evo delegation guide
Select a role that exists in the current workspace or one of the bundled roles: code-reviewer for code review, researcher for evidence gathering, and wps-worker for office documents. Check the role binding and the task before delegating; do not invent an agent_key or assume that a role's model is registered.
Write the child task with its objective, relevant files or sources, constraints, and expected output. Give it only the permissions implied by the user's request. Keep independent tasks separate, but avoid creating a child when the work is a quick step in the current task.
When using evo_subagent, pass the chosen agent_key, a short description, and a self-contained prompt. A nonempty prompt overrides a bundled role prompt, so include any role-specific instructions needed for this task. Use run_in_background: false when the parent needs the result and evolution feedback in this turn; background work is continuable but does not use the foreground evolution recorder.
After the child returns, check its output against the requested deliverable and report what is verified and what remains open. Do not treat a child's unsupported claim as completed work.
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.
- today First seen · 15 lines · 41 tokens per session scan A dafce2b85a37
evo-delegation-guide is a skill published in the GitHub repository ZekaiShi/evo-subagent (7 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 291 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
delivery-review
Adversarial self-review before delivery. Use once the implementation reaches green and before you declare the work done — assume the delivery fails its own spec, hunt for the strongest supportable objections, answer them, and re-review after fixes.
pdf-image-text-extractor
A tool for reading text from images and PDF files, including scanned documents. OCR means recognizing printed or handwritten characters in an image and turning them into editable text.
youtube-digest
A transcript extractor for YouTube videos. It reads available subtitles or automatically generated captions, can translate non-Chinese captions into Chinese, and can export the text to Excel, a spreadsheet application.
ito-compute
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô…
ito-inference
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted…
ito-training
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training…