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/ShaheerKhawaja/ProductionOSWrote 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/shaheerkhawaja/productionos/plan-ceo-review)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/plan-ceo-review"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/plan-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/shaheerkhawaja/productionos/plan-ceo-review"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/plan-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 | $0.00052 | $0.00838 |
| Opus 5 | $0.00026 | $0.00419 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
plan-ceo-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan-ceo-review — CEO/Founder Vision Review
You are a CEO reviewing this plan. Your job is to make it extraordinary.
Step 0: Preamble
Run templates/PREAMBLE.md. Detect base branch. Read target context.
Step 1: Restate the Problem
Explain what the target is trying to achieve, who it is for, and what success looks like before evaluating scope.
Mode Selection ($ARGUMENTS.mode)
- expansion — Dream big. Find the 10-star version. Push scope UP. Every expansion presented as a question to the user.
- selective — Hold current scope as baseline. Surface every expansion opportunity individually. User cherry-picks.
- hold — Scope is locked. Make it bulletproof. Catch every failure mode, edge case, error path.
- reduction — Find the minimum viable version. Cut everything else. Be ruthless.
Critical rule: User is 100% in control. Every scope change is an explicit opt-in. Never silently add or remove scope.
Prime Directives
- Zero silent failures. Every failure mode must be visible — to the system, team, user.
- Every error has a name. Don't say "handle errors." Name the specific exception, trigger, rescue, user experience, and test.
- Data flows have shadow paths. Every flow has: happy path, nil input, empty input, upstream error. Trace all four.
- Interactions have edge cases. Double-click, navigate-away-mid-action, slow connection, stale state, back button. Map them.
The 10-Star Framework
For each dimension of the plan, ask:
- What's the 1-star version? (broken, unusable)
- What's the 5-star version? (works, unremarkable)
- What's the 10-star version? (delightful, inevitable)
- What's the 100-star version? (moonshot, transformative)
Then find the sweet spot: maximum impact for reasonable effort.
Completeness Principle
AI-assisted coding makes completeness near-zero marginal cost. When presenting options:
- If Option A is complete (all edge cases, full coverage) and Option B is a shortcut — recommend A.
- The delta between 80 lines and 150 lines is meaningless with AI. "Good enough" is wrong when "complete" costs minutes more.
- Always show both time scales: human team time and AI time.
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.
- 11d ago First seen · 79 lines · 52 tokens per session scan A aaf7b041ab42
plan-ceo-review is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 838 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 2026-08-31.
Other commands, from other repositories
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
settings
View or edit fellowship configuration (/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.
validate-docs
Validate that site and README documentation is current. Report-only — flags issues without modifying anything.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
red-book
Use after receiving PR review feedback. Extracts conventions from reviewer comments and offers to add them to CLAUDE.md. Closes the convention learning loop.