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/claude-code-workflows --skill subagents-orchestration-guidegit clone --depth 1 https://github.com/shinpr/claude-code-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/claude-code-workflows/subagents-orchestration-guide)<a href="https://agentmods.dev/skills/shinpr/claude-code-workflows/subagents-orchestration-guide"><img src="https://agentmods.dev/badge/skills/shinpr/claude-code-workflows/subagents-orchestration-guide/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/claude-code-workflows/subagents-orchestration-guide"><img src="https://agentmods.dev/badge/skills/shinpr/claude-code-workflows/subagents-orchestration-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 121 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 170 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00033 | $0.06891 |
| Opus 5.5 | $0.00013 | $0.02756 |
| Sonnet 5.5 | $0.00007 | $0.01378 |
| Haiku 4.5 | $0.00003 | $0.00689 |
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 17d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagents Orchestration Guide
Role: The Orchestrator
Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in the invoked recipe. Execute each applicable call when its prerequisites are met.
The orchestrator owns workflow decisions, routing, progress management, user interaction, the investigation and validation needed for those decisions, and explicitly assigned mechanical operations, using any available tool. Named specialists own explicitly assigned investigation and semantic deliverable creation or modification; invoke them before producing or changing code, tests, configuration, documents, task files, or other artifacts.
Workflow Subagent Context — Mandatory
This workflow's specialists are already self-contained through their agent definitions, loaded skills, and referenced artifacts. The smallest valid Agent prompt is the most reliable: the complete prompt is the exhaustive set of canonical field: value entries declared by the specialist's input contract. Preserve each value's meaning from its authoritative source and apply the canonical serialization declared for that field. This output discipline supersedes general-purpose prompt self-containment because added context competes with the specialist's loaded process and can prevent coherent completion.
This section governs the orchestrator's Agent prompt. Each specialist's agent definition owns its input acceptance and resolves its operational inputs. The orchestrator supplies the canonical contract entries unchanged.
First Action Rule
When receiving a new full-cycle task, retain the user's complete wording in the orchestrator and invoke requirement-analyzer with the Requirement Evidence Handoff below. Compare its scope evidence, cost evidence, and questions against that retained wording to judge requirement convergence and Structural Scale in the orchestrator. Dedicated design recipes use their own codebase-scoped bootstrap.
Requirement Evidence Handoff: pass requirements as the shortest verbatim user wording of the problem or desired user-visible or operational outcome, using an orchestrator working summary only when no such wording exists; pass context as the shortest user reason needed to interpret that outcome plus an environmental constraint only when it is essential. Keep the remaining requirement detail in the orchestrator for comparison after the result returns. The handoff supplies an evidence target; the retained wording supplies product requirements and exclusions. Classify evaluation requests, speculative ideas, and prescribed mechanisms from that retained wording rather than from the returned evidence, because a classification produced by an analyzer is inference presented in the same object as observation.
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.
- 17d ago Changed · +5 lines 2535b5d6d14c
- 1mo ago Changed · +2 lines 4fa84fde7cdb
- 1mo ago Changed bb7937ec6d22
- 1mo ago Changed df754b256f89
- 1mo ago Changed · -1 lines b170f6f34457
- 1mo ago Changed 770c990eee22
- 1mo ago Changed f83f423e59e3
- 1mo ago First seen · 309 lines · 33 tokens per session scan A fefaf600b443
subagents-orchestration-guide is a skill published in the GitHub repository shinpr/claude-code-workflows (701 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 6,891 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
handoff
Create a self-contained temporary handoff document when the user asks to transfer the session to a new chat or runs /handoff.
minimalism
Use in any coding session when writing or changing code — enforces the laziest solution that actually works (YAGNI, stdlib-first, shortest diff) while never trimming validation, error handling, security, accessibility, or the pipeline's tests/gates. Also triggers on "minimalism", "be lazy", "simplest/minimal…
build-guard
Use when implementing features, refactors, or multi-file changes. Orchestrated plan-then-execute with subagent dispatch and regression checkpoints.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…