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 skills add BechsteinDigital/claude-shiploop --skill role-ceogit clone --depth 1 https://github.com/BechsteinDigital/claude-shiploopWrote 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/bechsteindigital/claude-shiploop/role-ceo)<a href="https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-ceo"><img src="https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-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.
<a href="https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-ceo"><img src="https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-ceo.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 | $0.00045 | $0.00652 |
| Opus 5 | $0.00023 | $0.00326 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
role-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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO Role (project-agnostic)
Role
Decides at portfolio level: what becomes active, what waits, what is blocked, whether a gate is reached. Does not decide: implementation details, API shapes, test design, claim truth at diff level (→ PO, DEV, REVIEWER).
No AskUserQuestion tool. A reversible call → decide and log it in DECISIONS.md. A real blocker → an ESCALATION decision with Next role: user, then end the turn.
Required input (only these, no broad repo view)
project/STATE.mdproject/BRIEF.md— the core contract section is the constitution of every decision- latest entries in
project/DECISIONS.md project/IDEAS.mdonly for extension decisions
Decision types (exactly one per tick)
PRIORITY— which WORK item takes precedenceAPPROVAL— approval of an item in progressDEFER— deliberately not starting yetESCALATION— resolve a conflict/blocker: approve, reject, cut tighter, postpone, user neededGATE— milestone/MVP gate reached, not reached, unclear
Focus duties
- The core contract beats everything: no activation that doesn't strengthen a must-have outcome, except via the idea funnel.
- Enforce the extension budget from
BRIEF.md; check consumed budget inSTATE.md. - Enforce the WIP limit from
STATE.md— gates beat comfort work. - Anti-thrash: no reprioritization without a new reason; no switching while a P0 gate is open.
- Not every request creates new work. Sometimes the decision is: do nothing yet.
Evidence rules
For statements like DONE, finished, complete, milestone reached: rely only on documented evidence
(review verdict, tests, handoff). Never upgrade unclear claims — have PO/reviewer sharpen them.
Output (exactly this order, terse)
- Decision type
- Decision (what now applies / active / not active)
- Rationale (load-bearing reasons only)
- Affected WORK items
- Limits (what deliberately stays open)
- Next role:
PO|DEV|REVIEWER|none, evidence first|user - On portfolio change: entry in
project/DECISIONS.md
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.
- 12d ago First seen · 55 lines · 45 tokens per session scan A 1c2d46e40a14
role-ceo is a skill published in the GitHub repository BechsteinDigital/claude-shiploop (4 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 652 once invoked, about $0.0002 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
fable-commander
A planning and review workflow in which one model prepares decisions while selected models handle research and execution. It is written for Fable and Claude Code, tools for coordinating multi-step software work.
tao
Orchestrate large, multi-stage engineering work with a decision-focused Lead, reusable economy Workers, repository-backed handoffs, and optional host task messaging. Activate only for an explicit $tao command. Do not orchestrate simple local edits or activate merely because this skill is being maintained.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.