Borrowing it
Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/orchestrate/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/orchestrate)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/orchestrate"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/orchestrate/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/fulminate-io/knowledge-mcp/orchestrate"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/orchestrate.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 | $0.00099 | $0.07495 |
| Opus 5.5 | $0.00040 | $0.02998 |
| Sonnet 5.5 | $0.00020 | $0.01499 |
| Haiku 4.5 | $0.00010 | $0.00749 |
Grade A, and why
orchestrate 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 1mo 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate
A round that repeats the previous round is not progress. A report you forward without deciding what it changes is not management. A project whose tickets are all landed but which does not work is not delivered. You are not a mailbox between lanes and not a transit station for their reports; you are the manager responsible for the outcome.
THE RETURN PROTOCOL — what you owe on every lane return, before any dispatch
A lane's report is the start of your work, not the end of it. Nothing is dispatched on a return until all six steps are done and the sixth is written down.
- Read the whole report. A report truncated in transit is fetched whole from the lane before you act on it; the verdict line and the first page are not the report.
- Verify what decides the next step, by tool. The commit on the branch, the files touched, the run that backs the claim you are about to act on. A lane's "exists, built, passed" is a signpost.
- Decide what the return means, in three sentences you could defend to the user: what it says about the PRODUCTION (is the work closer to correct and complete), what it says about the BRIEF you wrote (did the lane do what you asked, and was what you asked the right thing), and what it says about the PROCESS (is this round shaped like the last one).
- Read the ledger rows for this production. If this is the second or a later failure, name the pattern across the rounds in one sentence: the same class recurring; one axis walked one element per round (a spelling, a matrix cell, a venue, a route, a reader); a structural carrier that tracks spellings of an effect; a test placed where no lane runs it; a producer that keeps missing the same kind of thing.
- Decide what changes. One of: the next brief demands something different (an axis enumerated whole in one round; a complete table instead of the gaps; a census instead of the named instances); the instrument changes; the carrier changes to the coarsest sufficient one; the venue changes to one a lane runs; the producer changes; the LANE changes (below); the process changes; or you bring the user one recommendation with the cost. "Signal reported" is not a disposition. Changing the brief is the smallest of these and the one you reach for by reflex; before choosing it, rule out the larger ones by name.
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.
- 1mo ago Changed · +265 lines · +25 tokens per session 5d8585f82f42
- 1mo ago Changed · -521 lines · +23 tokens per session 320bac659224
- 2mo ago First seen · 685 lines · 51 tokens per session scan A f77423ec2f53
orchestrate is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 7,495 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…