zoom-out

A code-exploration command that maps a file, code area, or idea to nearby modules, callers, dependencies, related decisions, and project terms.

In plain words
What is it for?
Use it to understand who uses a module, what it depends on, and which project decisions or glossary terms affect it.
Why use it?
It gives developers context before editing unfamiliar code and helps reveal connections that are easy to miss when viewing one file alone.

Command

Install

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.

agentmods
npx agentmods add commands/rajconnects/founder-stack/zoom-out
Clone the repo
git clone --depth 1 https://github.com/rajconnects/founder-stack
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00861
Opus 5 $0.00020 $0.00430
Sonnet 5 $0.00008 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 2d ago against content hash 900d670ef5fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

workflow/commands/zoom-out.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running a context-broadening pass. The user is unfamiliar with this area and needs a map before editing.

Arguments: $ARGUMENTS

Steps

  1. Resolve the focus.

    • If $ARGUMENTS is a file path, that's the focus.
    • If $ARGUMENTS is a module/concept name, find the file(s) that own it.
    • If $ARGUMENTS is empty, infer focus from the conversation's most recently-read file.
    • If you can't infer, ask.
  2. Read project conventions. Read .claude/project.json. Extract:

    • glossary_doc + glossary_anchor — to use the project's vocabulary, not generic terms.
    • decision_records.path and decision_records.format — to surface relevant prior decisions.
    • stack and frontend_root / backend_root — to scope the search appropriately.
  3. Build the map. Use the Explore subagent (if available) or direct Read/Grep/Glob:

    • Module under focus. Confirm what it is in glossary terms, not framework terms. (Not "the FooHandler" — "the [Glossary Term] intake module.")
    • Direct callers. Grep for imports/calls. Cap at top 10 by call frequency.
    • Direct dependencies. What this module reads from, writes to, or depends on.
    • Sibling modules. Other modules in the same conceptual scope.
    • Tests. Existing test files exercising this module.
    • Relevant decision records. Search decision_records.path for any record whose topic mentions the focus area or glossary terms in play. List the topic + status + 1-line resolution summary.
    • Architecture notes. If architecture_notes is configured, list filenames whose names mention the focus area.
  4. Print the map. Use this structure:

    ## Focus
    [glossary-aware one-liner of what this is]
    
    ## Callers (top N by frequency)
    - <caller> — <what it asks of this module>
    
    ## Dependencies
    - <dep> — <what we ask of it>
    
    ## Siblings (same scope)
    - <sibling> — <what it owns>
    
    ## Tests
    - <path> — <what it covers>
    
    ## Relevant decisions
    - [trace-id] <topic> — <resolution> (status: <resolved/open>)
    
    ## Architecture notes
    - <filename> — <relevance>
    
    ## Glossary terms in play
    - <term>: <definition from glossary>
    
  5. End with one open question. Based on what you mapped, propose one question you'd ask before editing this area — the question whose answer would most reduce risk. Do not propose a plan; that's what /spec-intake is for. The output of /zoom-out is a map, not a plan.

Read the full file on GitHub · 68 lines

Changes

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.

  1. 2d ago First seen · 68 lines · 41 tokens per session scan A 900d670ef5fb

Subscribe to this mod's changes

zoom-out is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 861 once invoked, about $0.0002 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.