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.
git clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/ceo-review)<a href="https://agentmods.dev/commands/fatihkan/badi/ceo-review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/ceo-review/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/commands/fatihkan/badi/ceo-review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/ceo-review.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 | $0.00000 | $0.00613 |
| Opus 5 | $0.00000 | $0.00307 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
ceo-review 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 2d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO/product review command. Challenges a feature or roadmap from the top — should we build it, for whom, what does success look like — via the product-strategist agent.
Required Tools
- Read (context, memory, specs)
- Grep / Glob (find related code and docs)
- Bash (git log / status for recent direction)
- Agent (delegate to product-strategist)
When to Use
Before committing engineering time to a feature, epic, or roadmap item. Run this when the question is "should we build this?" — not "how do we build it?". Pair with /eng-review once the bet is green-lit.
Procedure
Step 1: Gather Context
- Read
memory.mdand any spec/brief for the proposed work. - Skim related code and prior decisions (
knowledge-base.md, recent commits) to understand what already exists. - Identify the user-stated goal in one sentence.
Step 2: Delegate to Product Strategist
Launch the product-strategist agent with the goal and context. Ask it to apply the CEO lens:
- Is this the highest-leverage thing to build now?
- Who is the user and what job does this do for them?
- What is the smallest valuable version?
- How will we measure success, and what would tell us to kill it?
Step 3: Synthesize the Verdict
From the agent's output, produce a clear decision:
- BUILD NOW — proceed; hand the bet to
/eng-review. - SHRINK & BUILD — proceed with the reduced scope named by the strategist.
- DEFER — not now; record why and the trigger to revisit.
- KILL — do not build; record the reasoning.
Step 4: Record the Decision
- Primary destination — the daily note (
daily-notes/DDMMYY.md): append the verdict, the bet, and the success metrics. On DEFER/KILL, add the reasoning and the trigger to revisit. memory.mdis optional and capped at 100 lines. Write to it only when the decision must survive across sessions (e.g., a KILL that must not be re-proposed). Then:- Run
wc -l .claude/memory.mdfirst. - If adding one line would push the file past 100, consolidate existing entries first so the result stays at or under 100 lines.
- Add at most one line (verdict + one-line rationale). Never append the full verdict/bet/metrics block there.
- Run
- If BUILD/SHRINK, capture the smallest-valuable-version scope for the engineering-manager (
/eng-review).
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.
- 2d ago Changed · +4 lines 092c510a9495
- 9d ago First seen · 43 lines · 0 tokens per session scan A 6e95b236927f
ceo-review is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 613 tokens. 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 commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
security-audit
Comprehensive security audit with scored posture assessment.
investigate
Systematic root-cause debugging — find the cause before writing any fix.
qa
Systematic QA testing of a web application — diff-aware, tiered, with fix-and-verify loop.
review-pr
Perform a comprehensive code review of a pull request.