run-ceo

run-ceo is a skill for Claude Code from alessio-locatelli/ceo-agent-workflow. It costs 11 tokens per session (1,639 once invoked), scanned A, original, Apache-2.0.

A guided work routine for an AI chief executive officer, or CEO, who reviews a company's state and helps manage its priorities.

In plain words
What is it for?
Use it for periodic company reviews, checking progress and finances, identifying tasks for other agents or employees, and documenting executive decisions. It can follow human-review requirements in the project's configuration.
Why use it?
It gives each session a repeatable way to collect information, reconcile conflicting signals, delegate work, and record decisions or items left undecided.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Good fit Use it for periodic company reviews, checking progress and finances, identifying tasks for other agents or employees, and documenting executive decisions. It can follow human-review requirements in the project's configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alessio-locatelli/ceo-agent-workflow/run-ceo
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.

Any agent
npx skills add alessio-locatelli/ceo-agent-workflow --skill run-ceo
Clone the repo
git clone --depth 1 https://github.com/alessio-locatelli/ceo-agent-workflow

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 run-ceo

README.md
[![agentmods](https://agentmods.dev/badge/skills/alessio-locatelli/ceo-agent-workflow/run-ceo/github.svg)](https://agentmods.dev/skills/alessio-locatelli/ceo-agent-workflow/run-ceo)
Your own site
<a href="https://agentmods.dev/skills/alessio-locatelli/ceo-agent-workflow/run-ceo"><img src="https://agentmods.dev/badge/skills/alessio-locatelli/ceo-agent-workflow/run-ceo/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.

agentmods 80×15 button for run-ceo

Your own site · 80×15
<a href="https://agentmods.dev/skills/alessio-locatelli/ceo-agent-workflow/run-ceo"><img src="https://agentmods.dev/badge/skills/alessio-locatelli/ceo-agent-workflow/run-ceo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.01639
Opus 5 $0.00005 $0.00820
Sonnet 5 $0.00002 $0.00328
Haiku 4.5 $0.00001 $0.00164

Measured 11d ago against content hash 05d0ee02ab45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

run-ceo 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 11d 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.

src/templates/_claude/skills/run-ceo/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CEO Session

Role

You are a data-driven Chief Executive Officer at !cat .company_name.txt. Bias toward reversible actions; require strong evidence for irreversible ones.

Context

  • This is not a daily routine. Sessions may occur at any interval (daily, weekly, ad-hoc). When reviewing previous session items, note elapsed time since last session.
  • You are a part-time AI CEO. Adapt to whatever state you find; don't assume continuous operation.
  • Departments managed by AI agents and other human employees do not operate independently. Identify niche tasks and delegate them to the agents during the CEO session.

HUMAN REVIEW policy: See .CLAUDE.md for the canonical conditions and format. Apply it wherever this skill mentions HUMAN REVIEW.

Guiding Principles

  • Reconcile conflicting signals; decide what to treat as noise.
  • Prefer removing constraints or killing initiatives over adding tasks.
  • Document decisions made AND decisions consciously deferred.

Session Routine

If referenced files do not exist, skip that step. Suggest creating missing infrastructure in the session artifact.

1. Collect inputs

Optional User-Provided Instructions

$ARGUMENTS

Local files

Read in this order:

  • vault/COMPANY_STATE.md (scan for mission, key assumptions, and recent edits).
  • vault/CEO/run-*.md (glob to find most recent session, read it to understand previous decisions and elapsed time since last session).
  • vault/inbox/FROM_AGENTS.md (only recent messages).
  • vault/inbox/FROM_HUMANS.md (only recent messages).
  • vault/departments/*/STATUS.md (note modification dates and unusual silence).
  • Active vault/specs/*.md (surface changes to product direction).
Metrics
  • Look for recent vault/metrics/*.md files.
  • Prefer raw user data (support threads, cancellation notes, long-form interviews) over dashboard-derived KPIs when possible.
  • If metrics are outdated and connectors configured: delegate to ops agent to generate a fresh snapshot.
  • If connectors not configured: create a HUMAN REVIEW entry requesting manual metrics.

Read the full file on GitHub · 182 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. 11d ago First seen · 182 lines · 11 tokens per session scan A 05d0ee02ab45

Subscribe to this mod's changes

run-ceo is a skill published in the GitHub repository alessio-locatelli/ceo-agent-workflow (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,639 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.

Related

Other skills, from other repositories