product-owner

A role for defining and checking product requirements and plans. A product owner represents what the product should achieve and coordinates decisions before implementation.

In plain words
What is it for?
It helps run product-owner sessions, clarify tickets, plan work, record decisions, create tasks, verify results, review completed work, and prepare deployment handoffs.
Why use it?
It gives new work a clear path from requirements and decisions to tasks, verification, review, and handoff.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fusebase-dev/fusebase-flow/product-owner
Any agent
npx skills add fusebase-dev/fusebase-flow --skill product-owner
Clone the repo
git clone --depth 1 https://github.com/fusebase-dev/fusebase-flow

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.01204
Opus 5 $0.00028 $0.00602
Sonnet 5 $0.00011 $0.00241
Haiku 4.5 $0.00006 $0.00120

Measured 2d ago against content hash b347f9a30616, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.agents/skills/product-owner/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Owner

Style: Mode-B-lite. Codex-visible activation bridge for the canonical Fusebase Flow Product Owner role. This skill exists so Codex skill discovery can find "Product Owner" even though the full role body lives in the role agent files.

Purpose

Activate the Product Owner workflow on surfaces where agents are not first-class slash commands. The canonical role instructions remain in agents/product-owner/AGENT.md and the Codex mirror .codex/agents/product-owner.md; this skill only routes discovery and activation.

When to invoke

  • Operator types /product-owner.
  • Operator asks to activate Product Owner, start a PO session, or use the Product Owner role.
  • Operator searches /product or /skills in Codex and expects the Product Owner option.
  • A new ticket needs Product Owner phases: Specify, Clarify, Plan, Decisions, Tasks, Verify, Review, or deploy handoff drafting.

Do not invoke when

  • The operator asks to implement, fix, test, or deploy code directly; use the AI Developer role/handoff path.
  • The task is /onboard or project vision capture; project-onboarding owns that flow after Product Owner activation.
  • The task is product documentation design; product-docs-first owns that workflow.
  • The task is app decomposition; product-apps-decomposition owns that workflow.

Required inputs

Input Where it lives If missing
Always-on Flow rules FLOW_RULES.md down to ## Amendment log Stop and read before acting
Product Owner role discipline flow-skills/role-discipline/references/product-owner.md Stop and read before acting
Canonical Product Owner role body agents/product-owner/AGENT.md Use .codex/agents/product-owner.md; if both are missing, stop and report mirror/canonical drift
Codex Product Owner mirror .codex/agents/product-owner.md Use canonical agents/product-owner/AGENT.md and report that mirror-agents.sh should be run

Procedure

  1. Read the Product Owner role body, preferring .codex/agents/product-owner.md on Codex and falling back to agents/product-owner/AGENT.md.
  2. Execute the role body's activation boot exactly enough to satisfy its PO-BOOT-BLOCK / PO-ACTIVATED checks; do not paste or fork the full role body into this skill.
  3. Continue as Product Owner under the eight-phase flow, starting at Specify unless the operator provides an active artifact or phase.
  4. Route any implementation request to an AI Developer handoff or fresh AI Developer session; do not write production code as Product Owner.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 2d ago First seen · 95 lines · 55 tokens per session scan A b347f9a30616

Subscribe to this mod's changes

product-owner is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 1,204 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.

Related

Other skills, from other repositories

lov-gh-tidy

Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…

lovstudio/skills · 95 tokens

iblai-api-apply

Platform application gate — turn membership into an apply/review process. Applicant apply/renew/submit flows (drafts, file uploads, fees, withdrawal), reviewer pipeline (list, stats, detail, per-student decisions, notes, waivers, admin override submit, blocks), post-acceptance placement tests and course assignments…

iblai/api · 119 tokens

iblai-api-crm

Manage an ibl.ai organization's CRM via the platform API — people, organizations, pipelines and stages, lead sources, deals (with stage-move/won/lost actions), activities, and tags. Org-wide sales/relationship management. Use for lead capture, pipelines, and deal flow.

iblai/api · 64 tokens

iblai-api-agent-support

Manage an ibl.ai agent's human-support tickets via the platform API — list and filter the tickets users raised with an agent (by agent, requester, status, session), read a ticket's conversation thread, reply as the support team, change ticket status, and close or delete tickets. Use when triaging or responding to…

iblai/api · 79 tokens

clickup-cli

ClickUp CLI for managing tasks, sprints, comments, statuses, and Docs. Use when the user needs to interact with ClickUp — creating/editing tasks, checking sprint status, adding comments, linking PRs, managing Docs and pages, or searching tasks. Prefer this CLI over raw API calls.

ulises-jeremias/agent-toolkit · 65 tokens

iblai-api-invite

Manage ibl.ai organization user invitations via the platform API — list invites (accepted/pending) and send invites individually or in bulk (CSV rows), with optional group assignment. Use when inviting users into an organization.

iblai/api · 49 tokens