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 commands/rajconnects/founder-stack/zoom-outgit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00041 | $0.00861 |
| Opus 5 | $0.00020 | $0.00430 |
| Sonnet 5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
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 — 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
-
Resolve the focus.
- If
$ARGUMENTSis a file path, that's the focus. - If
$ARGUMENTSis a module/concept name, find the file(s) that own it. - If
$ARGUMENTSis empty, infer focus from the conversation's most recently-read file. - If you can't infer, ask.
- If
-
Read project conventions. Read
.claude/project.json. Extract:glossary_doc+glossary_anchor— to use the project's vocabulary, not generic terms.decision_records.pathanddecision_records.format— to surface relevant prior decisions.stackandfrontend_root/backend_root— to scope the search appropriately.
-
Build the map. Use the
Exploresubagent (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.pathfor 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_notesis configured, list filenames whose names mention the focus area.
-
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> -
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-intakeis for. The output of/zoom-outis a map, not a plan.
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 · 68 lines · 41 tokens per session scan A 900d670ef5fb
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.