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/datit309/supergraph/zoom-outnpx skills add datit309/supergraph --skill zoom-outgit clone --depth 1 https://github.com/datit309/supergraphWhat 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 | $0.00053 | $0.00460 |
| Opus 5 | $0.00026 | $0.00230 |
| Sonnet 5 | $0.00011 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
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.
What it actually says
/supergraph:zoom-out
One prompt. One map. Re-orient fast.
Announce: "🔭 /supergraph:zoom-out — stepping back..."
Steps
1. Read CONTEXT.md for domain vocabulary (if exists):
head -60 CONTEXT.md 2>/dev/null
2. Get architecture overview:
Use codebase-memory-mcp with CBM_PROJECT: call get_architecture for
overview, layers, boundaries, clusters, and hotspots; then use named
contract recipes hubs, bridges, and test-gaps. If unavailable, label it
unavailable and fall back to Serena/filesystem evidence.
3. Output module map using domain vocabulary from CONTEXT.md:
[Project name] — module map
[Community/Module A]
└── [file/symbol] — [one-line role in domain terms]
└── [file/symbol] — [one-line role]
[Community/Module B]
└── ...
Key flows:
[User action] → [Module A] → [Module B] → [output]
Hub nodes (high-change risk): [list]
Bridge nodes (coupling chokepoints): [list]
No implementation details. Domain language only. If a concept doesn't have a name in CONTEXT.md — use the most natural domain term and suggest adding it.
Rules
- Use domain vocabulary, not file/class names (prefer "payment processing" over "PaymentService.ts")
- If CONTEXT.md is missing or empty — use the most natural terms you can infer and note at bottom: "CONTEXT.md missing — terms inferred"
- No action items, no recommendations — orientation only
- Follow with: "Ready to /supergraph:plan, /supergraph:analyze, or /supergraph:architecture?"
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 · 52 lines · 53 tokens per session scan A 3539b1aa47ff
zoom-out is a skill published in the GitHub repository datit309/supergraph (21 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 460 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
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
migrate
Inventory an existing spec-driven project and apply bounded migrations to jig defaults: report, adopt-layout, rename-decisions, split-slices, slice-to-spec, seed-decisions, and copy-machinery. Use when the user says migrate this project to jig, adopt jig here, this repo already has specs — set up jig, scaffold-init…
adr-workflow
Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…
bug-fix
Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOTCAUSED → FIXING → REVIEWED → DONE, with VERIFIED, ESCALATED, and RESOLVEDONMAIN paths where needed. Auto-fires on fix this bug, debug this, root-cause this, this regressed…
vision-elicitation
Lightweight baseline elicitation pass that fills in docs/product-vision.md and the five docs/architecture.md elicitation slots after scaffold-init. Auto-triggers when you say set up project vision, elicit architecture, define what we're building, run the vision wizard, refresh the project pitch, or capture product…
analyze
Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity, underspecification, principle violations, coverage gaps, and terminology drift. Auto-triggers when you say analyze this spec, check for inconsistencies, audit…