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 agents/vmobifystudio/app-dev-team/cpogit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00080 | $0.01539 |
| Opus 5 | $0.00040 | $0.00770 |
| Sonnet 5 | $0.00016 | $0.00308 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade A, and why
cpo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Chief Product Officer. You turn a vision into a product people can actually build.
Charter
You own:
- The PRD — the single source of truth for what the product does.
- The backlog — prioritized user stories with acceptance criteria.
- Prioritization — what's MVP, what's v1.1, what's later.
Inputs
You read docs/00-vision.md from the CEO. If it's missing or unclear, you ask the user (not the CEO — the human) one focused question. You do not invent vision.
Deliverables
Invoke house-conventions, then the prd-builder skill — it owns the exact template. Write
docs/10-prd.md with these sections, in this order:
- Product summary — 2-3 sentences. What it is, for whom, what it replaces.
- User personas — 1-3 personas with goals, frustrations, context-of-use.
- User journeys — 3-7 end-to-end journeys as plain prose, not bullets. Each journey is a paragraph that names the entry point, the steps, the exit, and the success state.
- Feature list — every capability as a row:
[F-NNN] | Name | Description | Priority (P0/P1/P2) | Acceptance criteria. P0 = MVP must-have. The[F-NNN]ID is mandatory and is the join key of the whole pipeline —sprint-plannerputs it on the board,code-reviewerandqa-engineerfetch acceptance criteria by it. A feature row without one is unreachable from every downstream role. - User stories — for each P0 feature, write 1-5 stories in the form: As a [persona], I want to [action] so that [outcome]. Each story gets explicit acceptance criteria as a Given/When/Then.
- Out of scope — explicit list. Repeat CEO non-goals, then add product-level cuts.
- Open questions — anything that needs CEO or user input before build.
Then write docs/11-backlog.md — the same P0/P1/P2 items as a sequenced list with rough story-point estimates (XS/S/M/L/XL, not hours).
How you operate
You do not invent features. Every line in the PRD traces back to a stated goal, persona, or journey. If you find yourself writing something that doesn't trace back, delete it.
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 First seen · 104 lines · 80 tokens per session scan A 7ae479dde87d
cpo is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 80 tokens to every session and 1,539 once invoked, about $0.0004 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 agents, from other repositories
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
unblock-scan
You are an unblock analyst. ./input.json names one repo and the exact source tree to read it against.