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 rundesk-ai/rundesk-cli --skill delegating-workgit clone --depth 1 https://github.com/rundesk-ai/rundesk-cliWrote 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/rundesk-ai/rundesk-cli/delegating-work)<a href="https://agentmods.dev/skills/rundesk-ai/rundesk-cli/delegating-work"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/delegating-work.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 | $0.00076 | $0.02344 |
| Opus 5 | $0.00038 | $0.01172 |
| Sonnet 5 | $0.00015 | $0.00469 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
delegating-work 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 8d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work to an outcome
Own the requested outcome until every required result is delivered and proved. Before acting, identify the outcome, scope, authority, required evidence, and definition of done. Keep optional findings separate from the required result.
Recover context before acting
When a referent, decision, owner, constraint, or prior result is missing, recover it from the current conversation, supported Rundesk history, and the project's current source in that order. Do not infer private history from a name, a nearby file, or another agent's memory. Separate observed facts, inferences, and unknowns. Ask only when the ambiguity changes the scope, authority, or required outcome; otherwise state the smallest safe assumption and continue.
If the needed context cannot be recovered, preserve the gap in the task and report it as a blocker. Do not turn an absent fact into a confident instruction or delegated brief.
Check your own skills before delegating
Before deciding to delegate, inspect your available skill descriptions and load each skill whose intent matches the work. Apply that guidance to the delegation decision: it may give you the domain knowledge, workflow, or tools to handle the task directly. If another agent remains materially better suited, use what you learned to make the scope, constraints, evidence, and definition of done precise.
A grant only makes a skill available; do not treat its body as already loaded. Do not load unrelated skills, and do not infer a target's responsibility from its skill list.
Decide whether to delegate
Count the full coordination cost: selecting and briefing a target, waiting for the return, reviewing its evidence, and integrating it. Work directly when that cost is not clearly outweighed by better speed, expertise, independence, or risk reduction. Ordinary conversation and simple documentation, formatting, copy-only, or mechanical changes normally stay direct unless a real specialist judgment or required independent review changes the balance.
What ships with it
2 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.
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.
- 8d ago First seen · 185 lines · 76 tokens per session scan A 0b6b0dde840f
delegating-work is a skill published in the GitHub repository rundesk-ai/rundesk-cli (6 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 2,344 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 2026-08-31.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.