ceo-brief

ceo-brief is a command for Claude Code from strale-io/strale. It costs 23 tokens per session (716 once invoked), scanned A, original, MIT.

A command for writing or checking a CEO morning brief, a concise business summary of a completed operating session.

In plain words
What is it for?
Use it after the day’s operating work is finished to prepare the five-part brief or validate an existing one.
Why use it?
It keeps the brief focused on conclusions and business patterns rather than unfinished work or a shortened activity log.

Command for Claude Code

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/strale-io/strale/ceo-brief
Clone the repo
git clone --depth 1 https://github.com/strale-io/strale

Made for: Claude Code.

Wrote 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.

agentmods badge for ceo-brief

README.md
[![agentmods](https://agentmods.dev/badge/commands/strale-io/strale/ceo-brief.svg)](https://agentmods.dev/commands/strale-io/strale/ceo-brief)
Your own site
<a href="https://agentmods.dev/commands/strale-io/strale/ceo-brief"><img src="https://agentmods.dev/badge/commands/strale-io/strale/ceo-brief.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 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 $0.00023 $0.00716
Opus 5 $0.00012 $0.00358
Sonnet 5 $0.00005 $0.00143
Haiku 4.5 $0.00002 $0.00072

Measured 4d ago against content hash 7896cfc35c01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ceo-brief 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 4d 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.

.claude/commands/ceo-brief.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ceo-brief — the founder-facing half of a daily run

Argument: $ARGUMENTS (empty = today's date; --check = lint the existing brief without rewriting it).

Do not run this before the operating work is finished. The brief is written from a completed day, not alongside one. If the session is still mid-investigation, say so and stop — a brief written early reports intentions as outcomes.

1. Read the authority

docs/company/DAILY-RUN.md Part 3. Do not work from memory of the format; the five sections and their order are a contract and the guard enforces them.

2. Gather the material

  • The operating record for today in handoff/_general/from-code/ — this is the input, and the one thing you must not simply shorten.
  • The commercial pack: cd apps/api && npx tsx scripts/commercial-brief.ts. Its "THE READING" block is what section 1 is built from. Use the conclusions, not the numbers; the numbers appear only where they carry the meaning.
  • docs/company/LESSONS.md — if anything today belongs to a failure family, the business fact is the pattern, not the incident.
  • docs/company/DECISION-QUEUE.md — the only legitimate source of section 5.

3. Write it

docs/company/briefs/YYYY-MM-DD.md, five sections in order, ~300–600 words:

  1. Business performance · 2. What materially changed · 3. Fixed automatically ·
  2. Working on now (max three, outcomes not tasks) · 5. Needs your decision.

Section 5 defaults to "Nothing needs your decision today." Before putting anything there, apply the charter's test: could further code inspection, production measurement, experimentation, or an existing decision resolve this? If yes, go and do that instead — including now, mid-brief. Anything that does belong carries all five fields: the choice, what is established, the options, your recommendation, the concrete consequence of each.

4. Check it

cd apps/api && npx tsx scripts/check-ceo-brief.ts

Fix every error. Then answer DAILY-RUN.md's seven editorial questions yourself — especially "is anything here only because engineering spent time on it", which the script cannot ask and which is the question the format exists for.

Read the full file on GitHub · 66 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. 4d ago First seen · 66 lines · 23 tokens per session scan A 7896cfc35c01

Subscribe to this mod's changes

ceo-brief is a command published in the GitHub repository strale-io/strale (4 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 716 once invoked, about $0.0001 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.