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 agentmods add skills/maxedapps/agent-skills/use-subagentsnpx skills add maxedapps/agent-skills --skill use-subagentsgit clone --depth 1 https://github.com/maxedapps/agent-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/maxedapps/agent-skills/use-subagents)<a href="https://agentmods.dev/skills/maxedapps/agent-skills/use-subagents"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/use-subagents.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 | $0.00082 | $0.01292 |
| Opus 5 | $0.00041 | $0.00646 |
| Sonnet 5 | $0.00016 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
use-subagents 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Subagents
Harness-agnostic how to delegate: split work, assign, isolate, verify, clean up.
- Owning workflows decide task goals; this skill defines how to delegate.
- Use whatever safe subagent mechanism the host provides.
- Host launcher/adapters own capability checks, launch, continuation, status, stop, and runtime-state cleanup — not this policy.
- Apply this policy with every launcher.
Delegate + split
When a safe launcher exists, delegate. “Small/easy” is not a reason to keep work in parent.
Parent keeps (strong reason only): framing/decomposition/synthesis · plan/tracker ownership · integrate/dispositions/acceptance · user comms · workspace + runtime cleanup · atomic no-judgment steps · explicit user prohibition
If you skip delegation, record why.
Split before launch:
- One independently verifiable outcome per lane
- Classify: reader · writer · independent validator
- Record scope, deps, expected output, join point
- Parallelize only independent lanes; coupled work → one awaited lane
- Cap fan-out by parent integrate/verify/cleanup capacity
- Prefer roles in
assets/agents/: scout · research · worker (adapt names to the launcher if needed)
Pick a launcher
Choose one accountable launcher per lane. Prefer one launcher for the whole workflow.
A launcher is safe only if it provides: exact cwd/context · permissions/write boundary · observable start/completion · output capture · timeout/bound · cancel when async · known cleanup ownership.
Candidates (first safe fit):
- Built-in / native subagent tools
- Host extension or plugin
- Catalog/runtime adapter skill for this harness
- Non-interactive agent CLI with the capabilities above
- Else: parent may execute; block only when delegation/independence itself is required
Never let two launchers control the same lane. Follow the chosen launcher’s mechanics for launch/status/stop/runtime cleanup.
Assignment contract
Build from assets/assignment-template.md + one profile in assets/agents/.
What ships with it
4 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.
- 4d ago First seen · 126 lines · 82 tokens per session scan A 0fe18454297d
use-subagents is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 20d ago), licensed MIT. It adds 82 tokens to every session and 1,292 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…