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.
npx agentmods add skills/suyoumo/clawprobench/ceo-setupnpx skills add suyoumo/ClawProBench --skill ceo-setupgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWhat 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 | $0.00060 | $0.04389 |
| Opus 5 | $0.00030 | $0.02194 |
| Sonnet 5 | $0.00012 | $0.00878 |
| Haiku 4.5 | $0.00006 | $0.00439 |
Grade A, and why
ceo-setup 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 3d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO / Manager — Commitment System Setup
IMPORTANT — tool calls are not optional. This skill is a setup procedure, not a summary to narrate. Do NOT emit any confirmation text (no "Done", no "✅ Your system is ready") until every tool call in Steps 1 through 7 has actually been executed and succeeded. If you skip to FINAL with a confirmation message, you have failed the task.
You are configuring the commitments system for an executive or manager. Their day is dominated by back-to-back meetings where decisions are made verbally, constant delegation (most commitments are "make sure someone else does X"), and information flowing both directions — team to executive (synthesis needed) and executive to team (tracking needed).
The system lives as a project at projects/commitments/. The project
is declared by writing files into that directory; no separate
project_create is needed.
Order of operations (sequential, one tool call at a time)
- Write
projects/commitments/AGENTS.md— declares the project, seeds the mission system prompt - Write
projects/commitments/context.md— records the executive's current delegation patterns - Write the schema README and calibration
- Create
commitment-triageandcommitment-digestmissions scoped to this project - Install two dashboard widgets under
projects/commitments/.system/widgets/ - Write the setup-complete marker
- Only after every tool call above has succeeded, emit the Step 8 confirmation text
Step 1: Declare the project
Writing any file under projects/commitments/ is the declaration that
the project exists — the engine auto-registers it and scopes missions
to it. Start with the agent instructions:
memory_write(
target: "projects/commitments/AGENTS.md",
content: "# Commitments (Executive)\n\nThis project tracks obligations, delegations, decisions, and parked ideas for an executive.\n\n## Operating principles\n\n- Most commitments are delegations — default `delegated_to` when someone else is mentioned.\n- Signals expire after 24 hours unless promoted — executives move fast, stale signals are noise.\n- Group digests by responsibility type: DELEGATED vs OWNED vs DECISIONS PENDING.\n- For `agent_can_handle` items, ask permission before acting.\n- Start conservative; increase autonomy only after the user confirms patterns.\n",
append: false
)
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.
- 3d ago First seen · 224 lines · 60 tokens per session scan A 6d67dcf9ccd1
ceo-setup is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 8d ago), licensed Apache-2.0. It adds 60 tokens to every session and 4,389 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
cron
Schedule reminders and recurring tasks.
lastlight-evals
Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…