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/fusebase-dev/fusebase-flow/zoom-outnpx skills add fusebase-dev/fusebase-flow --skill zoom-outgit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWhat 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 | $0.00092 | $0.01303 |
| Opus 5 | $0.00046 | $0.00651 |
| Sonnet 5 | $0.00018 | $0.00261 |
| Haiku 4.5 | $0.00009 | $0.00130 |
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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Out (FR-20)
Style: Mode-B-lite. Concise, structured, AI-consumable.
Purpose
Stop patch-myopia. Before fixing a bug or making an improvement, zoom out and confirm the change addresses the root cause and stays consistent with the bigger picture — instead of stacking a narrow patch that creates drift elsewhere. Operationalizes always-on rule FR-20.
When to invoke
- About to commit a bug fix or behavior change that is non-trivial.
- The same file / function / area has been patched before (repeat-patch smell).
- A fix touches shared logic, data shape, an interface, or cross-app behavior.
- Operator says "fix X", "why does X keep breaking", "patch", "quick fix".
- Active phase is Implement or a post-gate fix.
Do not invoke when
- Trivial typo / formatting / comment-only edit.
- Pure net-new feature with no existing code to reconcile against.
- The work is reproduce-before-fix itself (that is FR-10 /
validation-and-qa) — run that first, then zoom out on the fix design.
Required inputs
| Input | Where it lives | If missing |
|---|---|---|
| The observed symptom / bug | operator report, logs, test output | run reproduce-before-fix (FR-10) first |
| Spec / decisions (if under a ticket) | docs/specs/<slug>/ |
proceed; note no spec to check against |
| North Star (if present) | docs/north-star.md |
skip the North-Star check silently (absent-by-default) |
Procedure
- Name the symptom vs the cause. State the visible failure, then the underlying cause. If you can only name the symptom, investigate before patching.
- Layer check. Is this the right place to fix it? (UI symptom caused by a data/API bug → fix the source, not the surface.)
- Consistency check. Does the fix contradict the spec, locked decisions, or
docs/north-star.md(if present)? If yes → stop, raise it. - Drift check. Will this patch create inconsistency elsewhere (other apps, shared logic, future edits)? Prefer the change that reduces total inconsistency.
- Repeat-patch check. Has this area been patched before? Two+ patches in one spot = treat as a design problem, not another patch.
- Decide — and emit the Required output block below. Either (a) produce a root-cause fix plan, or (b) justify a deliberate narrow patch ("symptom-level fix is correct here because …"). Never an unexamined patch.
- Ambiguous bigger picture → ask the operator in chat (FR-19); do not guess.
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.
- 2d ago First seen · 103 lines · 92 tokens per session scan A dac07aad392b
zoom-out is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 92 tokens to every session and 1,303 once invoked, about $0.0005 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
adobe-express-core
Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.
adobe-express-monetization
Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.
adobe-express-spectrum-ui-ux
Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…
adobe-express-cors-and-backend
Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…
adobe-express-document-manipulation
Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.
adobe-express-oauth-authentication
Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.