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.
git clone --depth 1 https://github.com/etrebels/claude-code-growth-osWrote 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/commands/etrebels/claude-code-growth-os/capture)<a href="https://agentmods.dev/commands/etrebels/claude-code-growth-os/capture"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/capture/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/commands/etrebels/claude-code-growth-os/capture"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.00479 |
| Opus 5.5 | $0.00006 | $0.00192 |
| Sonnet 5.5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
capture 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 1mo 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
Capture
A frictionless inbox so a passing thought doesn't cost you a context switch. Two modes — drop and triage. The inbox is a staging buffer, never a second to-do list.
Drop (default — when I hand you a note)
- Append the note verbatim to
inbox/notes.md, one dated line per item:- [YYYY-MM-DD HH:MM] <the note>. Create the file if it's absent. - Confirm in one line. Do not act on it, file it, expand it, or ask follow-ups — the whole point is to not break my focus.
Triage (when I say "triage the inbox" / "process capture")
Walk inbox/notes.md top to bottom. Route each item to the lane that owns it — never let a captured note become a parallel task list (see .claude/rules/todo-single-source.md):
- A task → the one task list (
ops/priorities.md, or your task tool). - Something said in a meeting → your notes / wiki lane.
- A deal change → the CRM /
ops/pipeline.md, per.claude/rules/crm-usage.md. - A post-sale signal →
ops/customers.mdorops/roadmap-signals.md(tagRETENTION-RISK/FEATURE-REQUEST). - A field-intel signal for marketing →
ops/feedback-log.md(MARKETING-ACTION). - A reference fact or a preference → the right
ops/ordocs/file. - Noise → delete it.
Remove each item from inbox/notes.md as you route it. Close with one line: routed N, deleted M, left K (and why each was left).
Depth
- quick: drop only.
- standard: drop, or triage the whole inbox.
- deep: triage, flag anything sitting more than 7 days, and propose a standing route for any capture pattern that keeps recurring.
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.
- 1mo ago First seen · 33 lines · 15 tokens per session scan A 75afdbd47c86
capture is a command published in the GitHub repository etrebels/claude-code-growth-os (21 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 479 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
slack-comms
Read, write, and manage Slack communications. Supports reading channel history, posting messages, summarizing threads, replying in threads, and posting structured action notifications.
comms-scan
Unified communication triage across email, social mentions, and project management in one pass.
monday
Monday morning startup sequence. Runs multiple commands in order with approval checkpoints, then opens the weekly dashboard.
audit-release
Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.
sugar-review
Review and manage pending Sugar tasks interactively.
go-to-market
Build a complete go-to-market strategy based on the requirements found in files.requirements.