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 oaustegard/claude-skills --skill dispatching-subagentsgit clone --depth 1 https://github.com/oaustegard/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/oaustegard/claude-skills/dispatching-subagents)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/dispatching-subagents"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/dispatching-subagents/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/oaustegard/claude-skills/dispatching-subagents"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/dispatching-subagents.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 | $0.00165 | $0.03210 |
| Opus 5.5 | $0.00066 | $0.01284 |
| Sonnet 5.5 | $0.00033 | $0.00642 |
| Haiku 4.5 | $0.00016 | $0.00321 |
Grade A, and why
dispatching-subagents scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
child can hold Bash with `Bash(curl:*)` refused; How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching subagents
Claude Code has three ways to start a subagent. They differ most in what the launching costs the parent.
| Agent tool | Workflow tool | claude -p children (scripts/headless_fanout.py) |
|
|---|---|---|---|
| parent cost | one parent turn per launch and one per completion | one tool call per run | one Bash call per run |
| concurrency | 20, and a 21st launch errors (it does not queue) | min(16, vCPUs − 2): 2 on a 4-vCPU CCotw container | RAM-bound, about 210 MB per child: 40 ran clean on 4 vCPU / 15 GB |
| child context | session prefix (~32–55K tokens), plus parent transcript chunks if a context hook is installed | session prefix | what you pass: about 1.2K tokens with --system-prompt and no tools, 39K with the default prompt |
| tools | agent type's tools, the session's MCP connectors, hooks | as Agent | built-in tools named in --tools, write paths allowlisted; no MCP, hooks or skills |
| effort | session's level, or the effort: in a named agent type's frontmatter |
agent(prompt, {effort}) |
--effort (measured: low gave 0 thinking tokens, high gave 112–197) |
| needs user opt-in | no | yes: an explicit request, ultracode, or a skill that calls it | no |
| cost visibility | none per child | none per child | total_cost_usd and tokens per child, in a ledger |
| output check | yours | in-script | file plus JSON Schema, or CLI-validated --json-schema |
The headless runner is the default for volume. On 2026-10-11 a codex build
dispatched 314 Haiku children through the Agent tool. The children cost
$11.61. The 1,458 Opus parent turns the dispatching took (each re-reading a
context of about 400K tokens) cost roughly $160–170, about 14× the work. Five of
the same tasks through headless_fanout.py cost $0.10, $0.02 each against
$0.033 per Agent-tool child, and one parent call.
Choosing
Answer in order. The first yes picks the mechanism.
- Does the child need what only the session has? That means MCP connectors
(Muninn, Gmail, GitHub MCP), a context hook's transcript chunks, a worktree,
or a custom agent type with guard hooks such as
auditor. If so, use the Agent tool. Keep the count small, or batch many items into each child, because every launch costs a parent turn. - Do you need to read each result before deciding the next launch? That is iterative work where task N+1 depends on N's answer. Use the Agent tool.
- Did the user opt in to a workflow, and does the procedure have phases a
script should enforce (find → verify → fix, with retries and gates)? Use
Workflow, and load
workflow-authoringfirst. Accept 2-way concurrency on a 4-vCPU container, or move the bulk phase to headless children. - Are there ten or more independent tasks whose inputs fit in a prompt or in files, and whose output a script can check? Use headless children. This covers judges, graders, extractors, page writers, verifiers and per-file reviews.
- Fewer than ten small independent tasks: use the Agent tool in one message. The parent-turn cost is still small at that size.
What ships with it
5 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.
- 2d ago Changed b87aba7ee0c4
- 3d ago Changed · +2 lines 1bb8d5a42b4b
- 4d ago Changed · +1 lines dbe4c0bb162f
- 5d ago First seen · 198 lines · 165 tokens per session scan A c7a49ce5e58e
dispatching-subagents is a skill published in the GitHub repository oaustegard/claude-skills (153 stars, last pushed yesterday), licensed MIT. It adds 165 tokens to every session and 3,210 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
Other skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
figma-to-code
Generate production-ready React/Next.js code from Figma designs. Instructs proper Figma MCP tool usage, component reuse strategies, and variant mapping. CRITICAL: ALWAYS use this skill when user provides a Figma link or mentions implementing/redesigning from Figma design. Never attempt manual implementation without…
smb-sales-boost
Find, preview and export growing local businesses (SMB leads) from the SMB Sales Boost database through its REST API - search by keyword, location and buying signals, preview for free, export CSV/JSON/XLSX, re-download past exports, enrich lists of website URLs, manage saved searches, keyword lists, email schedules…
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
balzac
Balzac is an AI content platform CLI. Create workspaces, manage SEO keywords, generate article suggestions, write articles, publish content across integrations, and monitor Google Search Console performance. Supports workspaces, keywords, suggestions, briefings, articles, competitors, links, integrations, search…
balzac
AI content platform CLI. Create workspaces, manage SEO keywords, generate article suggestions, write articles, and publish to WordPress, Webflow, Wix, GoHighLevel, or webhooks.