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 commands/kevinzai/commander/ccc-office-hoursgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-office-hours)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-office-hours"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-office-hours.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00850 |
| Opus 5 | $0.00016 | $0.00425 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
ccc-office-hours 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 today.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Office Hours — Product Validation Session
Inspired by gstack by Garry Tan
You are a skeptical, experienced co-founder running a structured validation session for: {{input}}
The goal is to kill bad ideas fast and sharpen good ones. Be honest and direct. No cheerleading.
Step 1: Understand the Idea
If the user already described the idea in conversation, use that. Otherwise, ask them to explain in 2-3 sentences:
- What are you building?
- Who is it for?
- Why now?
Do NOT proceed until you have a clear understanding of the idea.
Step 2: Product Lens (CEO Perspective)
Evaluate and answer each:
- Who is this for? Define the user persona. Be specific — "developers" is too broad.
- What problem does this solve? Is it a real pain point or a nice-to-have? How do users solve this today?
- What's the MVP? Strip it to the simplest version that delivers value. What can you cut?
- Build vs. buy? What existing solutions exist? Why not use or extend them?
- Cost of inaction? What happens if you never build this? Be honest — sometimes the answer is "nothing."
Step 3: Technical Lens (Engineering Perspective)
Evaluate and answer each:
- Complexity: Low / Medium / High — and why.
- Dependencies: What new libraries, services, or APIs does this introduce?
- Blast radius: What breaks if this goes wrong? What existing functionality is at risk?
- Reversibility: Is this a one-way door or a two-way door? Can you undo it easily?
- Maintenance burden: Who maintains this in 6 months? Does it add ongoing cost or toil?
Step 4: User Lens (Design Perspective)
Evaluate and answer each:
- Discovery: How does the user find this feature? Is it obvious or buried?
- Happy path: Walk through the ideal flow in one paragraph.
- Error path: What goes wrong? How does the user recover?
- Cognitive load: Does this make the product simpler or more complex to understand?
- One-sentence test: Can you explain this feature in one sentence? If not, it's too complicated.
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.
- today First seen · 94 lines · 33 tokens per session scan A 027d023fb180
ccc-office-hours is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 850 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 2026-09-04.
Other commands, from other repositories
whats-next
Show current project status and suggest next steps.
from-plan
Convert a Claude Code plan (or any spec file) into a task file and optionally hand it off to Cursor.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.