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 shinpr/codex-workflows --skill subagent-delegationgit clone --depth 1 https://github.com/shinpr/codex-workflowsWrote 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/shinpr/codex-workflows/subagent-delegation)<a href="https://agentmods.dev/skills/shinpr/codex-workflows/subagent-delegation"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/subagent-delegation/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/shinpr/codex-workflows/subagent-delegation"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/subagent-delegation.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 | $0.00043 | $0.00643 |
| Opus 5.5 | $0.00017 | $0.00257 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Delegation
Apply this skill before delegating work or managing a running subagent. It covers both custom agents and agents created for the current task.
Delegation gives the child a responsibility and the authority to complete it from an isolated context. Pass only the task's minimum input contract; preloading the parent's conclusions, target list, or classifications turns delegation into confirmation work, suppresses independent judgment, and defeats context isolation.
Assignment
Give the child its expected outcome, scope, governing inputs required by its input contract, and the result needed by the next consumer. Pass artifact paths instead of repeating their contents. Leave in-scope methods and reversible choices to the child. Tell the child to notify the parent when its decision or intervention is needed or an update is explicitly requested, and otherwise work through to the completed result; include the evidence needed to act.
Accept semantically equivalent wording in natural-language inputs while preserving exact contracts where software parses them.
Choose the delegation level before spawning, based on which decisions the child owns:
| Task type | Default delegation |
|---|---|
| Implementation or fixes within confirmed scope; review or verification against supplied criteria; research with a defined question | Delegate through completion, including the required verification. Receive the completed result or an escalation for a blocker requiring help beyond the child's assigned scope. |
| Exploration or design that needs the parent to settle the objective, selection criteria, or a major decision during the work | Name the decision retained by the parent in the assignment. Have the child request that decision when it becomes necessary, with the evidence needed to answer. |
Research and design also use completion delegation when the child can make the required decisions from its assigned scope and evidence. Use these defaults directly; only a retained parent decision needs additional consultation instructions.
What ships with it
1 file 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 Changed 3612440e4b6f
- 28d ago Changed · +2 lines 3411d6ba270d
- 1mo ago Changed 6c001b03bd56
- 1mo ago Changed · +2 lines · -2 tokens per session c5d2fcf3f047
- 1mo ago First seen · 32 lines · 45 tokens per session scan A 70016e3f4770
subagent-delegation is a skill published in the GitHub repository shinpr/codex-workflows (39 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 643 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
notifications
Send notifications through the unified notification router.