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 Jeffallan/writing-with-agents --skill whirlybirdgit clone --depth 1 https://github.com/Jeffallan/writing-with-agentsWrote 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/jeffallan/writing-with-agents/whirlybird)<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/whirlybird"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/whirlybird/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/jeffallan/writing-with-agents/whirlybird"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/whirlybird.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 | $0.00039 | $0.02008 |
| Opus 5 | $0.00019 | $0.01004 |
| Sonnet 5 | $0.00008 | $0.00402 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
whirlybird 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Definition
The Whirlybird is the nonlinear outlining phase using Bryan Garner's technique from The Winning Brief. Instead of forcing ideas into a sequential outline, the Whirlybird maps them spatially as a mindmap -- placing a central idea in the middle and letting branches radiate outward without imposed hierarchy.
Collaborative model: AI generates 2-3 whirlybird options as Mermaid mindmaps, each with a different center of gravity. Human selects, combines, or redirects. The human never receives a single take-it-or-leave-it structure.
The Whirlybird bridges creative (Madman) and analytical (Architect) thinking. The Madman produces raw material without restraint. The Architect imposes order with a throughline. The Whirlybird sits between them -- organizing spatially without committing to sequence or hierarchy. Ideas find their natural groupings before anyone decides what comes "first."
Priority is not assigned during this phase. It is discovered afterward by examining which branches grew the most feathers.
When to Use This Skill
- After the Madman phase has produced raw material that needs spatial organization
- When exploring multiple structural angles for a single piece
- When mapping a knowledge domain for content strategy planning
- When a sequential outline feels premature or forced
- When the writer is stuck choosing between competing approaches
- When you need to visualize relationships between ideas before committing to hierarchy
- When planning a content cluster and need to see the territory before dividing it
- When raw material from multiple sources needs to be unified under a single spatial view
- When a piece keeps changing direction and you need to see all candidate framings at once
- When onboarding a collaborator who needs to see the shape of the argument visually
- When evaluating whether a topic has enough substance for a full article or should be combined with another
- When decomposing a complex topic into subtopics to determine where natural article boundaries fall
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.
- 11d ago First seen · 141 lines · 39 tokens per session scan A d56ed3afbe5b
whirlybird is a skill published in the GitHub repository Jeffallan/writing-with-agents (31 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 2,008 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…