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/mgd34msu/goodvibes-plugin/task-orchestrationnpx skills add mgd34msu/goodvibes-plugin --skill task-orchestrationgit clone --depth 1 https://github.com/mgd34msu/goodvibes-pluginWrote 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/mgd34msu/goodvibes-plugin/task-orchestration)<a href="https://agentmods.dev/skills/mgd34msu/goodvibes-plugin/task-orchestration"><img src="https://agentmods.dev/badge/skills/mgd34msu/goodvibes-plugin/task-orchestration.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 | $0.00054 | $0.00727 |
| Opus 5 | $0.00027 | $0.00364 |
| Sonnet 5 | $0.00011 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
task-orchestration 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-orchestration
v1's orchestration text predates native multi-agent workflow support and was written around a bespoke runtime engine (a background daemon coordinating agents via IPC, directives, and a phase-machine). That daemon is cut for v2. The deep review found no standing usage that justified keeping a background process running per session, and native Task/Workflow tooling already covers the observed needs. This skill is the rebuild: orchestration using what the platform gives you directly, plus the WRFC template as a pattern, not infrastructure.
Decomposing work
Break a task into steps where each step:
- Has a single agent type responsible for it (engineer, tester, refutation-reviewer, architect).
- Has an explicit "done" condition, not a vague direction ("implement the API" is not a step; "implement POST /api/posts per the spec architect produced, with the validation and error cases it lists" is).
- States its real dependencies: which steps must finish first, and what output they hand off.
Independent steps (no shared dependency) can run as parallel Task-tool calls in the same turn. Dependent steps run sequentially, with each agent's output feeding the next agent's task description directly. Don't route it through a shared mutable file unless the next agent actually needs to read that file itself.
The WRFC pattern: Write → Review → Fix → Confirm
For any change worth reviewing before it ships:
- Write. The engineer agent implements the change.
- Review. The refutation-reviewer agent reviews the actual diff (see the
review-scoringskill for the rubric: a defect list with severity, not a scalar score). - Fix. If the review found
CONFIRMED critical/highdefects, the engineer addresses them. Cap this at a small, explicit number of iterations (2-3). An unbounded fix loop is a sign the task needs re-scoping, not more iterations. - Confirm. The FIX gets reviewed too, not assumed correct. Only after a fix iteration passes review (or the loop is explicitly capped and escalated to the user) is the change done.
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.
- 5d ago First seen · 56 lines · 54 tokens per session scan A b534e0e5bd97
task-orchestration is a skill published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 12d ago), licensed MIT. It adds 54 tokens to every session and 727 once invoked, about $0.0003 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 2026-08-31.
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…
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…