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 magic3007/dotfiles --skill toil-offloadinggit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/magic3007/dotfiles/toil-offloading)<a href="https://agentmods.dev/skills/magic3007/dotfiles/toil-offloading"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/toil-offloading.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01832 |
| Opus 5 | $0.00043 | $0.00916 |
| Sonnet 5 | $0.00017 | $0.00366 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
toil-offloading 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toil Offloading
Keep the root agent as orchestrator, not the default implementer. The root owns goal clarification, decomposition, cross-cutting analysis, architectural and priority decisions, assignment boundaries, conflict resolution, integration, and final acceptance. Delegate the bounded execution work: repository searches, diagnosis, implementation, refactoring, data extraction, artifact generation, and focused verification.
Subagents are not read-only by default. Give them the write scope and local validation needed to finish their assignments. Use read-only assignments only when the work is genuinely inspection-only, the user requested it, or write isolation cannot be made safe.
Use only the native collaboration tools exposed by the current Codex runtime.
Do not launch agent CLIs or codex exec as shell subprocesses.
Start with real work
Do not create availability, model-identity, provider-routing, or capability probe assignments. Treat the agent types advertised by the runtime as the session contract and send the first useful assignments directly. If an assignment cannot start or finish, record its actual outcome and continue other safe, useful work. Reassign only when the task scope and acceptance condition remain explicit; never replace a native worker with a shell subprocess.
Route work
- Select agent types from the runtime descriptions according to task complexity, cost, and the evidence the assignment must produce.
- Prefer lightweight worker roles for targeted searches, inventories, extraction, formatting, repetitive validation, focused test execution, and small independent edits with an obvious acceptance condition.
- Prefer stronger reasoning roles for cross-file analysis, ambiguous diagnosis, non-trivial implementation, conflict analysis, or independent review.
- Keep architectural decisions, destructive or externally mutating actions, conflict resolution, final integration, and acceptance with the root agent.
- Let workers make ordinary implementation decisions inside their assignment contract. Ask them to return cross-cutting choices or scope changes to the root instead of silently expanding the assignment.
- If an assignment exposes materially different complexity, finish or close it and create a new bounded assignment with a suitable agent type. Do not silently change roles or scope.
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 Changed · +62 lines 4e867f67503b
- 4d ago First seen · 96 lines · 86 tokens per session scan A 174c802a6efc
toil-offloading is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,832 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec.
use-notion
Reference for using the Notion API via the notion-agent subagent. Use to expore and update Notion workspace content.
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
extend-oss-skills-to-claude
Extend standard agentskills.io skills with Claude Code-specific features. Invocation control, subagent execution, dynamic context injection, string substitutions, model/effort overrides, and deployment scoping. Use when adapting a portable skill for Claude Code, adding Claude-specific frontmatter, setting up subagent…