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 HiAgencia/hi-claude --skill delegationgit clone --depth 1 https://github.com/HiAgencia/hi-claudeWrote 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/hiagencia/hi-claude/delegation)<a href="https://agentmods.dev/skills/hiagencia/hi-claude/delegation"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/delegation/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/hiagencia/hi-claude/delegation"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/delegation.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 | $0.00147 | $0.00812 |
| Opus 5 | $0.00073 | $0.00406 |
| Sonnet 5 | $0.00029 | $0.00162 |
| Haiku 4.5 | $0.00015 | $0.00081 |
Grade A, and why
delegation 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation (hi-claude)
A subagent INVESTIGATES. It never decides what gets done and never touches the project's artefacts — a PreToolUse policy enforces that, with no escape switch. This skill is the other half: what the dispatcher asks for, and what it does with what comes back.
Before dispatching
- Delegate the LOOKING, never the DECIDING. "Find every place X happens, with
file:line" is a task. "Decide whether we should migrate" is not — that one is yours, and a subagent asked for it returns a confident answer you cannot audit. - Never delegate the change. Not an additive one, not a rename, not a "quick fix". The main agent applies every change, so the reasoning behind an edit lives in one place.
- Name the evidence you want back:
file:line, the command that reproduces it, the payload, the row. A finding without evidence cannot be verified, which makes it unusable here. - Different lenses beat more agents. Three copies of one question find one thing. Dispatching several is worth it when each carries a distinct angle — say the angle in its prompt.
- Scope it so the answer is checkable. If you would not know how to disprove the report, the task was too broad to be worth delegating.
When the report comes back
- Read it whole, not a summary of it. What a subagent brings is INPUT to your judgement, never a substitute for it.
- Verify first-hand before anything rests on it. Open the file, run the command, read the row. A finding is a HYPOTHESIS until you have seen the thing yourself — and this applies just as much to a report that agrees with you as to one that does not.
- A confident tone is not evidence. Rank findings by what was shown, never by how it was phrased.
- What does not survive verification is struck WITH the datum that struck it. That is worth as much as a confirmed finding, and it stops the same claim from returning next month.
- You own the decision, and you say it in your own words. The report never decides.
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.
- 11d ago First seen · 53 lines · 147 tokens per session scan A f0d9098445a8
delegation is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 21d ago), licensed MIT. It adds 147 tokens to every session and 812 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…