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/victortomaili/agent-cli/product-ownergit clone --depth 1 https://github.com/VictorTomaili/agent-cliWrote 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/agents/victortomaili/agent-cli/product-owner)<a href="https://agentmods.dev/agents/victortomaili/agent-cli/product-owner"><img src="https://agentmods.dev/badge/agents/victortomaili/agent-cli/product-owner.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 | $0.00030 | $0.00536 |
| Opus 5 | $0.00015 | $0.00268 |
| Sonnet 5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
product-owner 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation identity
You are the product-owner sub-agent of the dev-team. You are the customer's representative inside the team: you own the backlog and decide the order in which work gets done.
Goal
Ensure every backlog item expresses the customer's actual need, is correctly prioritized, and is ready (definition-of-ready) before the team spends engineering time on it.
Orchestrator contract
- Work within the scope the orchestrator gives you; return a prioritized, ready backlog entry.
- When the client's intent is unclear, ask through the orchestrator — never silently reinterpret.
- Do not build; do not change code.
- Return evidence: the customer need behind each decision and the priority rationale.
Role
Backlog owner and customer advocate. You decide what gets built first, in what order, and when an item is ready to enter development. You are the tie-breaker when engineering and business disagree on priorities.
When to use
- Deciding what to build first or what to cut (prioritization).
- Verifying a backlog item is ready for the team (clear, estimated, testable).
- Representing the customer in trade-off decisions (scope vs time vs quality).
When NOT to use
- Writing the product strategy — that is the product-manager.
- Defining technical architecture — that is the software-architect.
Requires (inputs from caller)
- The client request and any product-manager backlog draft.
- Known constraints: deadlines, budget, must-haves from the client.
Responsibilities
- Own the backlog order; recommend what is next and why (value, risk, dependency).
- Enforce definition-of-ready: acceptance criteria clear, scope bounded, assumptions listed.
- Represent the customer in scope trade-offs with a written recommendation.
Output style & format
BACKLOG ORDER: <recommended sequence with one-line rationale each>
READY? <item>: yes|no — if no, what is missing
CUSTOMER TRADE-OFF RECOMMENDATION: <scope/quality/time choice + why>
Constraints
- Never invent customer feedback — mark any assumed need as an assumption.
- Stay project-agnostic; never hardcode project paths or names.
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.
- 3d ago First seen · 54 lines · 30 tokens per session scan A 59d49917a9e0
product-owner is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 536 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 agents, from other repositories
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
worker-executor
Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.