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 tslateman/duet --skill zoom-outgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/zoom-out)<a href="https://agentmods.dev/skills/tslateman/duet/zoom-out"><img src="https://agentmods.dev/badge/skills/tslateman/duet/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/tslateman/duet/zoom-out"><img src="https://agentmods.dev/badge/skills/tslateman/duet/zoom-out.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 | $0.00068 | $0.00607 |
| Opus 5 | $0.00034 | $0.00303 |
| Sonnet 5 | $0.00014 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00061 |
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 8d 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.
Zoom Out
Overview
When you don't know a section of code well, the failure mode is to read line-by-line and never see the shape. Zoom out forces a higher layer of abstraction first: callers, neighbors, role in the system. Read the map before walking the streets.
The Map First
Before explaining what a piece of code does, produce a map of its surroundings:
- Identify the unit: file, module, package, or service. Name it precisely.
- Find callers: who uses this? Grep for imports, invocations, or routes.
- Find neighbors: what siblings live in the same directory or namespace, and what do they do?
- Find the abstraction above: what does this module belong to? A pipeline, a layer, a bounded context.
- Find the abstraction below: what does it depend on?
Render the result as a short list or small diagram. Use the project's own vocabulary: the words the codebase uses, not generic CS terms.
Output Shape
Aim for something like:
Module: src/billing/invoicing/
Role: Generates invoices from billing periods (one of three writers under /billing)
Above: /billing — orchestrates subscriptions, invoicing, dunning
Below: /billing/pricing (rates), /billing/tax (tax calc)
Callers: src/jobs/monthly_invoice_job.py, src/api/admin/invoices.py
Siblings: subscriptions/, dunning/
Then, and only then, go deeper.
Anti-Patterns
- Reading line-by-line first. A bottom-up model rarely survives contact with the actual architecture.
- Generic vocabulary. "Service layer, repository pattern" tells the reader nothing about this codebase. Use its own terms.
- Skipping callers. Behavior at the callsite often constrains the module more than the module's own code does.
- Zooming in too soon. If the map isn't done, every implementation detail you read is uncalibrated.
Pairs With
/naming: domain vocabulary lives in names; zoom-out is naming applied to architecture/design: zoom-out surfaces the structure, design evaluates it/ia: IA is zoom-out for documentation; same instinct, different medium/research: zoom-out maps the inside, research maps the outside
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.
- 8d ago First seen · 56 lines · 68 tokens per session scan A a5d036847329
zoom-out is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 12d ago), licensed MIT. It adds 68 tokens to every session and 607 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
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.
architect
Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…
designer
Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…
setup-working-genius
Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.