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 haowjy/creative-writing-skills --skill zoom-outgit clone --depth 1 https://github.com/haowjy/creative-writing-skillsWrote 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/haowjy/creative-writing-skills/zoom-out)<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/zoom-out"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/zoom-out/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/haowjy/creative-writing-skills/zoom-out"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/zoom-out.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00534 |
| Opus 5.5 | $0.00012 | $0.00214 |
| Sonnet 5.5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
zoom-out 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 10d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Out
Load /creative-writing-skills:qi-layer if it isn't already loaded.
Orient in an unfamiliar area by fanning out parallel explorers, each covering a different angle, then synthesizing their reports into one orientation map. A single explorer sees one slice; zoom-out covers structure and knowledge and history at once, so the picture isn't skewed by one lens.
Use when starting in an unfamiliar subsystem, picking up someone else's work, or when the user says "orient me" / "what's the lay of the land here."
Fan Out
Spawn in parallel the angles the area has material for, each scoped to one angle and one question.
- Structure (
@explorer): how the area's parts connect and where behavior lives; in code, callers, dependencies, module boundaries, entry points. - Documented knowledge (
@explorerover the knowledge base): what's been written about this area, including architecture, guides, synthesized research. - Decision history (
@session-miner): why it's shaped this way. Prior choices, rejected alternatives, constraints discovered. - Domain concepts (
@explorer): the vocabulary in use (KB vocab pages,.context/CONTEXT.md, AGENTS.md).
Give each explorer one angle, scoped with concrete path or topic targets: the value is independent coverage.
Synthesize
Read the reports and produce one orientation map, not stitched-together dumps:
- What this is: the area's purpose and boundaries, in two or three sentences.
- Structure: the parts and interfaces that matter and how they connect (a mermaid diagram if the shape is spatial).
- Why it's like this: the decisions and constraints that explain the current shape.
- Vocabulary: the terms needed to speak about it precisely.
- Open threads: gaps, debt, or unresolved questions the explorers surfaced.
When reports contradict each other, resolve it rather than listing both, by what each source governs: the thing itself (the code, the data, the manuscript) shows its current state, and a settled decision shows intent. A doc that misdescribes current state is stale (note it); a gap between current state and settled intent is a divergence to report. Keep the map tight: the goal is a reader who can now navigate the area, not an exhaustive transcript.
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.
- 10d ago Changed · -6 lines · +1 tokens per session d2ebb039570d
- 2mo ago First seen · 44 lines · 30 tokens per session scan A 3b61e9852a61
zoom-out is a skill published in the GitHub repository haowjy/creative-writing-skills (567 stars, last pushed 10d ago), licensed Apache-2.0. It adds 31 tokens to every session and 534 once invoked, about $0.0001 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 2026-08-30.
zoom-out compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zoom-outhaowjy/creative-writing-skills | Skill | 567 | 10d ago | Apache-2.0 | A | 31 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |