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 mbruhler/claude-orchestration --skill creating-workflows-from-descriptiongit clone --depth 1 https://github.com/mbruhler/claude-orchestrationWrote 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/mbruhler/claude-orchestration/creating-workflows-from-description)<a href="https://agentmods.dev/skills/mbruhler/claude-orchestration/creating-workflows-from-description"><img src="https://agentmods.dev/badge/skills/mbruhler/claude-orchestration/creating-workflows-from-description.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.01030 |
| Opus 5 | $0.00013 | $0.00515 |
| Sonnet 5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
creating-workflows-from-description 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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Workflows from Description
When to Use
Proactively suggest orchestration when user describes tasks involving:
- Multiple sequential steps with dependencies
- Parallel operations that could run simultaneously
- Conditional logic or branching (if/then scenarios)
- Error handling or retry requirements
- Testing, review, and deployment phases
- Complex multi-agent coordination
- Quality gates or approval checkpoints
Trigger Patterns
Watch for these patterns in user messages:
Explicit workflow requests:
- "I need to [multi-step task]"
- "Help me build a pipeline for [process]"
- "Create a workflow that [description]"
- "Automate [complex task]"
Implicit workflow descriptions:
- User describes 3+ sequential steps
- User mentions temporal ordering: "then", "after that", "once that's done"
- User mentions conditionals: "if that works", "if tests pass"
- User mentions parallel work: "at the same time", "in parallel", "simultaneously"
- User mentions reviews/approvals: "needs review", "after approval"
- User mentions retry/error handling: "if it fails", "retry", "rollback"
Example phrases:
- "run tests, then if they pass..."
- "deploy to production after security review"
- "implement with TDD workflow"
- "check code quality before merging"
- "parallel test execution"
Action
When triggers detected, suggest orchestration:
This sounds like a perfect use case for orchestration! I can help you create a workflow that handles:
[List 2-4 key aspects identified from description, e.g.:]
- Sequential testing and deployment steps
- Parallel validation (tests + security scan)
- Conditional deployment based on test results
- Automatic rollback on failure
Would you like me to guide you through creating this workflow?
If user says yes:
Execute the create command with their description:
/orchestration:create [initial description from user message]
If user says no or wants to see example first:
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.
- 8d ago First seen · 147 lines · 26 tokens per session scan A 5fb63d133588
creating-workflows-from-description is a skill published in the GitHub repository mbruhler/claude-orchestration (219 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,030 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…