Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/etrebels/claude-code-growth-osnpx agentmods add commands/etrebels/claude-code-growth-os/end-of-dayWrote 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/end-of-day)<a href="https://agentmods.dev/commands/etrebels/claude-code-growth-os/end-of-day"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/end-of-day/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/end-of-day"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/end-of-day.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 | $0.00012 | $0.00655 |
| Opus 5.5 | $0.00005 | $0.00262 |
| Sonnet 5.5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
end-of-day 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End of Day
Generic chassis variant. If a private operating repo (e.g. your own growth-os) defines a command with this name, that version is canonical for that repo's data.
Close out the day:
- Ask me what got done today (or infer it from
git logsince this morning) — across both sides of the bowtie: deals worked and post-sale touches (onboarding steps, adoption nudges, renewal/expansion moves, signals routed to product). - Append a dated entry to
ops/daily-log.md(newest at the top): shipped, slipped, one thing learned. Log post-sale work alongside deals — a renewal call or an adoption fix counts the same as a deal advanced. - Persist & reconcile the CRM. Write the day's stage/score/note changes back per
.claude/rules/crm-usage.md, then reconcile the mirror — rewriteops/pipeline.mdfrom the CRM so tomorrow opens consistent. Skip if no CRM is connected. - Lion check. If a task keeps rolling forward behind a citable obstacle, name it plainly, then sort it. A thing repeatedly deferred behind the same reason is usually avoidance, not a blocker — decide: do it tomorrow, or drop it. But if the obstacle is a real blocker, don't just park it behind the block either — name at least one route around it: a smaller version you can ship now, a different path to the same outcome, or the specific person who can unblock it. A blocked item leaves the close with a next action, never just a later date.
- Draft tomorrow's top three into
ops/priorities.md. - Confirm what you wrote — and log every CRM write (
object · field · old → new). Keep it tight.
Depth
- quick: log one line (shipped / slipped) and tomorrow's top item.
- standard: the full close above.
- deep: add what to stop doing and a 7-day pattern note.
Closing step — record the run (never skip)
A run that died and a run with nothing to say must not look alike. Finish by writing the outcome to disk, from the repo root:
bash .claude/scripts/routine-state.sh ok end-of-day "<what landed — one short line>"
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 Changed · +18 lines aa3f326fbe3f
- 1mo ago First seen · 22 lines · 12 tokens per session scan A c48f1e4f0729
end-of-day is a command published in the GitHub repository etrebels/claude-code-growth-os (21 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 655 once invoked, about $0.0000 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
show-your-work
Keep a reviewable TSV decision trail for long-running or unattended work. Usage: /show-your-work [task-slug].
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
fire-todos
Capture, list, and manage todos during work sessions.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
start
Get oriented with ArcKit — guided project onboarding, workflow selection, and command recommendations.
my-tasks
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.