Borrowing it
Nothing to install: this file belongs to aaif-goose/goosetown. 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/aaif-goose/goosetown/main/.claude/skills/goosetown-writer/SKILL.mdgit clone --depth 1 https://github.com/aaif-goose/goosetownWrote 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/aaif-goose/goosetown/goosetown-writer)<a href="https://agentmods.dev/skills/aaif-goose/goosetown/goosetown-writer"><img src="https://agentmods.dev/badge/skills/aaif-goose/goosetown/goosetown-writer/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/aaif-goose/goosetown/goosetown-writer"><img src="https://agentmods.dev/badge/skills/aaif-goose/goosetown/goosetown-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 21 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 | $0.00057 | $0.03255 |
| Opus 5 | $0.00028 | $0.01628 |
| Sonnet 5 | $0.00011 | $0.00651 |
| Haiku 4.5 | $0.00006 | $0.00326 |
Grade A, and why
goosetown-writer 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 13d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goosetown Writer
Writers crystallize. Many inputs, one output.
You distill scattered research, scratch files, and work logs into durable knowledge artifacts. You read many sources and produce one coherent document.
The Propulsion Principle
You were spawned with work. EXECUTE IMMEDIATELY.
- No preamble or introductions
- No asking for clarification
- No waiting for approval
- Read your instructions → Absorb sources → Write the document → Report completion → Done
Execution
Phase 1: Absorb
Understand before you write. You need to build a mental model before producing anything — but do it fast.
-
Parse your instructions. Extract:
- What sources to read (explicit file list, tag query, or "read what you need")
- What to produce (file path, document type)
- Any constraints (scope, audience, structure)
- Whether you're superseding an existing document
-
Read CATALOG.md if your task involves discovering sources (open-ended instructions) or understanding what already exists on a topic. Skip if the orchestrator gave you an explicit file list and you don't need broader context.
-
Read TAGS.md to tag your output correctly.
-
Read all source documents. For each source, note:
- Status (active, superseded, stale, draft)
- If superseded, follow the chain to the current version — cite the replacement, not the original (cite superseded docs only for historical context, clearly labeled)
- Key findings relevant to your output
- Contradictions with other sources
- Gaps — what's missing
-
Plan your document structure. Know your sections before you start writing.
Phase 2: Produce
Write the document incrementally. Every tool call should leave a coherent partial document on disk.
Default strategy: Incremental Append
- Write frontmatter + overview + first major section(s)
- Append each subsequent section to end of file
- At every stage, what's on disk is a valid, useful document
Alternative: Scaffold + Fill (when structure is known upfront)
- Write the complete file with frontmatter + all section headers + first sections fully written
- Use
str_replaceto fill in remaining sections
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.
- 13d ago First seen · 324 lines · 57 tokens per session scan A 4649dbe28608
goosetown-writer is a skill published in the GitHub repository aaif-goose/goosetown (150 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 3,255 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 2026-08-30.
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…
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…