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 Magnus-Gille/claude-skills --skill m5-delegategit clone --depth 1 https://github.com/Magnus-Gille/claude-skillsWrote 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/magnus-gille/claude-skills/m5-delegate)<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/m5-delegate"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/m5-delegate/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/magnus-gille/claude-skills/m5-delegate"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/m5-delegate.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 | $0.00027 | $0.00877 |
| Opus 5 | $0.00014 | $0.00439 |
| Sonnet 5 | $0.00005 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
m5-delegate 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
M5 Local Delegation
Use this skill when local inference is requested or an applicable delegation policy calls for a self-contained leaf. The goal is to save frontier tokens and produce useful real delegation data for the home-server project.
When To Use It
Once activated, suitable leaves include:
- Summarize, classify, extract, rewrite, draft.
- Short, bounded reasoning where an approximate answer is acceptable.
- Single-shot code generation with a clear spec.
- Batch harnesses that can run on the M5 box itself.
Avoid it:
- Work needing the full current repo or conversation context.
- Security-critical reasoning or tasks where a wrong answer is costly to detect.
- Multi-step code edits unless a caged code-loop style tool is explicitly available.
- Private content unless it will stay on a local-only path.
Model/Runtime Guidance
- Prefer a fast non-thinking model such as
mellumfor short classify/extract/summarize/simple-codegen. - Use
qwen3-coder-next-80bfor harder coding or agentic-coding leaves. - Use
gemma4for general or multimodal tasks when relevant. - Discover available models and current tool schemas before choosing; the names above are examples, not an availability guarantee. Size output budgets to the task and detect truncated or empty results.
- Batch independent same-model calls when supported to avoid unnecessary model swaps; measure runtime rather than assuming fixed latency.
Access Paths
Prefer purpose-built MCP tools if they are available in the current agent session, such as list_models, ask, or code_loop_*.
Always pass the cloud delegator model when you know it:
- MCP
ask: includedelegator_model_id, for example"delegator_model_id": "openai/gpt-5.5". - Direct
/delegate: includedelegatorModelId, for example"delegatorModelId": "openai/gpt-5.5". - Homeserver CLI: pass
--delegator <cloud-model-id>.
Use the actual frontier/conductor model for the current task, not a generic default. This is what lets the M5 ledger measure actual savings rather than only premium-baseline savings. If the cloud delegator is unknown, omit the field instead of guessing.
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.
- 5d ago First seen · 70 lines · 27 tokens per session scan A ab47c4163e29
m5-delegate is a skill published in the GitHub repository Magnus-Gille/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 27 tokens to every session and 877 once invoked, about $0.0001 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 2026-09-06.
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…