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/alessio-locatelli/ceo-agent-workflownpx agentmods add skills/alessio-locatelli/ceo-agent-workflow/verify-projectWrote 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/skills/alessio-locatelli/ceo-agent-workflow/verify-project)<a href="https://agentmods.dev/skills/alessio-locatelli/ceo-agent-workflow/verify-project"><img src="https://agentmods.dev/badge/skills/alessio-locatelli/ceo-agent-workflow/verify-project/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/skills/alessio-locatelli/ceo-agent-workflow/verify-project"><img src="https://agentmods.dev/badge/skills/alessio-locatelli/ceo-agent-workflow/verify-project.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 | $0.00008 | $0.02143 |
| Opus 5 | $0.00004 | $0.01071 |
| Sonnet 5 | $0.00002 | $0.00429 |
| Haiku 4.5 | $0.00001 | $0.00214 |
Grade A, and why
verify-project 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 10d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Project Setup
You are performing a comprehensive validation of the CEO Agent Workflow project setup. This verification ensures the user has properly configured the system after running init_startup.sh and before running /company/run-ceo.
Validation Process
Phase 1: Automated Checks
Run the automated validation script:
bash .claude/scripts/verify-project-automated.sh
Record the results and any errors/warnings from the automated script.
Phase 2: Semantic Configuration Review
Thoroughly review each configuration file for completeness and coherence:
1. COMPANY_STATE.md Validation
Read vault/COMPANY_STATE.md and verify:
Mission & Vision
- Company mission is specific and actionable (not generic)
- Vision statement is clear and measurable
- Industry/market is clearly defined
Team Section
- At least one founder/employee is listed with real name
- Roles are specific (not just "Founder" but "Founder, CEO" or "Founder, CTO")
- If advisors are listed, they have specific expertise areas
Budget & Runway
- Total budget is a realistic number (not exactly $10,000)
- Burn rate makes sense for team size
- Runway calculation is correct: (Total Budget - Spent) / Burn Rate
- Cash allocation percentages add up to 100%
Product Status
- Current stage matches the specs in
vault/specsdirectory - Tech stack is specific (not "TBD" or "Various")
- If MVP is claimed, there should be corresponding deployment info
Quarterly OKRs
- Objectives are specific to this business (not generic template text)
- Each objective has 2-3 measurable key results
- Key results have specific numbers/dates
- No placeholder dates like "2024-01-15" or "End of Q1"
Avoid XY Problems, Wishful Thinking, and Unsupported Statements
- Provide justification or references for important statements. Bad: “Framework X is slow.” Better: “Framework X is slow because …” (include a clear reason or evidence). Bad: “Tool X is not suitable.” Better: “In my opinion/personal experience, Tool X is not suitable.” (emphasize that this is a personal judgment rather than an absolute fact).
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.
- 10d ago First seen · 296 lines · 8 tokens per session scan A 7e82679b1139
verify-project 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 8 tokens to every session and 2,143 once invoked, about $0.0000 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 skills, from other repositories
github-tool
GitHub integration tool for listing and creating issues and PRs via the gh CLI wrapper. Use when: creating or listing issues or pull requests, or checking repository work on GitHub.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.