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/shinpr/codex-workflows/subagents-orchestration-guidenpx skills add shinpr/codex-workflows --skill subagents-orchestration-guidegit 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/subagents-orchestration-guide)<a href="https://agentmods.dev/skills/shinpr/codex-workflows/subagents-orchestration-guide"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/subagents-orchestration-guide.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 | $0.00038 | $0.05689 |
| Opus 5 | $0.00019 | $0.02844 |
| Sonnet 5 | $0.00008 | $0.01138 |
| Haiku 4.5 | $0.00004 | $0.00569 |
Grade A, and why
subagents-orchestration-guide 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 today.
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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagents Orchestration Guide
Spawn rule: every spawn_agent call uses fork_turns="none" so the subagent receives only the task message and explicitly provided context.
Role: The Orchestrator
The orchestrator owns workflow state and directly performs lightweight coordination: locating artifacts, reading status fields, resolving paths, applying explicit user answers, updating execution plans and approval fields, running deterministic repository checks, and composing specialist inputs. Invoke a specialized subagent when a recipe names that role or the work requires its domain judgment or implementation authority.
Execution Plans
Reuse one active execution plan for the recipe. When none exists, create it before substantive multi-step work with the recipe phases and final verification, then update the same plan as evidence is produced. Agent-internal execution plans remain local to each agent. Plans prevent skipped work; their wording or presence is not a user approval gate.
Prompt Construction Rule
Give each subagent the expected action and the artifact paths or evidence needed for that action. Follow the agent's input contract and supply facts not already carried by the artifact. A compatible value under different wording is usable. Resolve a missing input when it would change the action or make its result unverifiable; use Orchestrator Escalation Resolution when repository and governing evidence cannot supply it.
Entry Ownership
The invoked recipe determines the workflow entry point. Recipes for new or scope-changing requirements may invoke requirement-analyzer for compact scope and cost evidence. The user and orchestrator retain requirements, Structural Scale, and ADR decisions. Continuation, build, review, diagnosis, document update, and reverse-engineering recipes resume from their declared artifacts and request new scope evidence only when their own scope-change rule fires.
Requirement Convergence
The orchestrator builds the convergence object from the user's wording and uses requirement-analyzer's scope and cost evidence for trade-offs, questions, and routing decisions. At the requirements stop, run the requirement-convergence hearing, then determine Structural Scale from the confirmed requirements and supplied evidence. User-confirmed boundaries supply requirements; orchestrator decisions supply routing.
What ships with it
3 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.
- today Changed · +1 lines 4bc8de5b6165
- 4d ago First seen · 345 lines · 38 tokens per session scan A 226433d6553b
subagents-orchestration-guide is a skill published in the GitHub repository shinpr/codex-workflows (37 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 5,689 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 2026-08-30.
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.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…