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 kraulerson/solo-orchestrator --skill zoom-outgit clone --depth 1 https://github.com/kraulerson/solo-orchestratorWrote 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/kraulerson/solo-orchestrator/zoom-out)<a href="https://agentmods.dev/skills/kraulerson/solo-orchestrator/zoom-out"><img src="https://agentmods.dev/badge/skills/kraulerson/solo-orchestrator/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/kraulerson/solo-orchestrator/zoom-out"><img src="https://agentmods.dev/badge/skills/kraulerson/solo-orchestrator/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 | $0.00066 | $0.00758 |
| Opus 5 | $0.00033 | $0.00379 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
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 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Out
Attribution. Adapted from mattpocock/skills (MIT, © Matt Pocock). The upstream is a one-paragraph prompt to "go up a layer of abstraction." Solo's adaptation points the zoom-out at the project's actual artifacts (PROJECT_BIBLE, phase-state, ADRs, backlog) so the map produced is grounded in canonical sources, not improvised. See
NOTICEfor full attribution.
I don't know this area of code (or this decision point) well enough. Go up a layer of abstraction. Produce a map that uses the project's actual vocabulary.
What to include
- Where we are. Current phase (read
.claude/phase-state.json), current Build Loop state (read.claude/process-state.json), current branch, current PR (if any). - The relevant code surface. Modules, files, and callers touching the area in question. Use the names that already exist in the codebase — not invented categories.
- The relevant decisions. Read
docs/ADR documentation/for any ADRs in this area. Cite them by number. If a decision is about to be made, ask whether an ADR should be opened. - The relevant architectural truth. Cross-reference
PROJECT_BIBLE.md(architecture, data model, threat model). IfPROJECT_BIBLE.mdand the code disagree on something material, surface the contradiction. - What's in flight. Read
solo-orchestrator-backlog.md(or the project's backlog) for any related open BL items. Note openpending-approval.jsonsentinels. - What the next decision actually depends on. Not "what could come next" — what is BLOCKED on what.
What to skip
- Long prose summaries of the codebase. The map is structural, not literary.
- Speculation about future features not on the backlog.
- Repeating content from
PROJECT_BIBLE.mdverbatim — link to it instead.
When this is most valuable
- Between features. After
process-checklist.sh --complete-step build_loop:feature_recorded, before the next--start-feature. The zoom-out is the natural Context Health Check moment (Builder's Guide § "Context Health Checks every 3-4 features"). - At a phase transition. Phase 2→3, Phase 3→4. Step back before crossing the gate.
- When debugging. Before diving into a hard bug, zoom-out tells you which other systems share the failure surface.
- When onboarding a successor or returning after a break. The map is the resumption substrate (pairs with
session-handofffor that case). - When stuck on a design decision. If the next step has two defensible paths, zoom-out surfaces the decisions and artifacts that should weigh on the choice.
What ships with it
1 file 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 · 41 lines · 66 tokens per session scan A 7291923d0b45
zoom-out is a skill published in the GitHub repository kraulerson/solo-orchestrator (29 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 758 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…
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…