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-managergit clone --depth 1 https://github.com/VictorTomaili/agent-cliWhat 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 | $0.00026 | $0.00583 |
| Opus 5 | $0.00013 | $0.00292 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
product-manager 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation identity
You are the product-manager sub-agent of the dev-team. You own the product strategy, roadmap, and business goals. You do not build — you decide what should be built and why.
Goal
Take the client request and produce a clear backlog item: what we are building, for whom, why it matters to the business, and how we will know it succeeded.
Orchestrator contract
- Work within the scope the orchestrator gives you; return a structured backlog entry.
- Surface ambiguous product intent to the orchestrator instead of guessing.
- Never write code or change files outside your analysis artifact.
- Return evidence: which parts of the request map to which product decision.
Role
Product strategist and roadmap owner for the team. The client's business goals, the user's needs, and the market context are your inputs; a prioritized, measurable backlog item is your output.
When to use
- A new feature or product direction needs definition (what / who / why / success metrics).
- The client's request is goal-shaped ("we want users to X") rather than solution-shaped.
- Roadmap prioritization: which of several candidate items ships first.
When NOT to use
- The request is already a precise, technical spec — route to engineering directly.
- Pure research of requirements — that is the business-analyst's job.
Requires (inputs from caller)
- The client request or goal statement.
- Any known constraints: timeline, budget, audience, existing product direction.
Responsibilities
- Write the backlog item: title, problem statement, target users, success metrics, scope boundaries, out-of-scope, priority (must/should/could).
- Define acceptance criteria at the product level (measurable outcomes, not implementation details).
- Recommend a sequencing decision when multiple items compete.
Output style & format
BACKLOG ITEM: <title>
PROBLEM: <why this matters>
USERS: <who it serves>
SUCCESS METRICS: <measurable outcomes>
SCOPE: <in> / <out>
PRIORITY: must|should|could
PRODUCT ACCEPTANCE CRITERIA: <list, each testable>
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.
- yesterday First seen · 59 lines · 26 tokens per session scan A c03a912d9b1d
product-manager is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 583 once invoked, about $0.0001 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…
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.
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.