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 PracticalSwan/agent-skills --skill subagent-delegationgit clone --depth 1 https://github.com/PracticalSwan/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/practicalswan/agent-skills/subagent-delegation)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/subagent-delegation"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/subagent-delegation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 109 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00040 | $0.01291 |
| Opus 5 | $0.00020 | $0.00646 |
| Sonnet 5 | $0.00008 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
subagent-delegation 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Delegation Patterns
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
Activate this skill when:
- Creating repetitive code structures or boilerplate
- Performing data transformation tasks
- Analyzing codebase for patterns or information
- Generating documentation from existing code
- Creating simple utility functions
- Breaking down complex features into manageable subtasks
Core Delegation Patterns
See Delegation Patterns for detailed examples of:
- Boilerplate generation (API routes, CRUD operations, component structures)
- Data transformations between formats
- File analysis and pattern extraction
- Documentation generation from code
- Utility function creation
Anti-Patterns
- Delegating or evaluating without a scoped success condition: The output becomes hard to review and easy to overbuild.
- Skipping the evidence step: A workflow that cannot be re-checked quickly is not ready for handoff.
- Bundling unrelated subtasks together: It creates noisy prompts, weaker ownership, and avoidable integration risk.
Verification Protocol
Before claiming "skill applied successfully":
- Pass/fail: The Subagent Delegation workflow names the agent boundary, delegated scope, and expected return artifact.
- Pass/fail: Context passed to helpers is minimal, task-local, and free of hidden expected answers.
- Pass/fail: Results are integrated only after evidence, diffs, or citations are checked by the controller.
- Pressure-test scenario: Run the workflow on two similar tasks that must not share assumptions or leaked context.
- Success metric: Zero context leakage; every delegated output is independently reviewable.
Examples & Scripts
- Delegation Pattern Examples — Code examples of common delegation patterns
- Delegation Template — JavaScript template for structuring delegation calls
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.
- 4d ago First seen · 140 lines · 40 tokens per session scan A f8c44ac22368
subagent-delegation is a skill published in the GitHub repository PracticalSwan/agent-skills (13 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,291 once invoked, about $0.0002 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
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.