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 skills add P47Phoenix/Claude-Plugins --skill product-deliverygit clone --depth 1 https://github.com/P47Phoenix/Claude-PluginsWrote 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/skills/p47phoenix/claude-plugins/product-delivery)<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/product-delivery"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/product-delivery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/product-delivery"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/product-delivery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00230 | $0.03531 |
| Opus 5.5 | $0.00092 | $0.01412 |
| Sonnet 5.5 | $0.00046 | $0.00706 |
| Haiku 4.5 | $0.00023 | $0.00353 |
Grade A, and why
product-delivery 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 1mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Delivery Agent
Design Principle: Role Context Isolation
This skill keeps role-specific knowledge out of the main context window. When a product delivery task is requested, the relevant role is detected, only the corresponding reference file(s) are loaded, and a sub-agent is spawned with that isolated context. The main context receives only the finished artifact.
Product delivery tasks can span roles -- sprint planning involves both Product Owner and Scrum Bag concerns, and metrics definition may involve both Data Analyst and Product Owner. When a task spans roles, multiple overlapping references are loaded into a single sub-agent.
Phase 1: Role Detection
Detect the relevant role from (in priority order):
- Explicit role mention -- "as a product owner", "scrum master perspective", "data analyst"
- Task type signals -- see routing tables below
- Domain signals -- story/backlog/PRD keywords route to Product Owner; ceremony/process/velocity keywords route to Scrum Bag; metrics/analytics/experiment keywords route to Data Analyst
If ambiguous, ask before proceeding. Do not assume.
Declare before every task:
Role: [ROLE] | Task: [TYPE] | References: [list of reference files]
Phase 2: Sub-Agent Invocation
For every product delivery task, follow these steps exactly -- do not skip:
- Detect the role and task type (Phase 1)
- Read only the relevant reference file(s) from the routing table -- do NOT read all reference files
- Spawn a sub-agent using the
Agenttool with the prompt template below - Return the sub-agent's output directly to the user
Do not inline role-specific knowledge into the main context. The sub-agent is the execution boundary for all role-specific reasoning.
Sub-Agent Prompt Template
You are an expert [ROLE]. Apply these principles and patterns to everything you produce:
---
[PASTE FULL CONTENTS OF EACH RELEVANT REFERENCE FILE -- separated by --- if multiple]
---
## Task
[TASK TYPE]: [DESCRIBE WHAT THE USER WANTS]
## Context
[Product/team, constraints, existing artifacts, sprint context, business drivers, related artifacts]
## Output Requirements
Produce the pattern artifact, explicit rationale, stated assumptions, open questions needing human decision, and next steps.
If modifying existing files, use Read, Edit, Write, Glob, and Grep tools directly.
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agile-metrics.md 6.8 KB
- references/analytics-patterns.md 7.3 KB
- references/backlog-management.md 5.4 KB
- references/dashboard-design.md 5.9 KB
- references/dependency-tracking.md 6.1 KB
- references/estimation.md 6.8 KB
- references/experimentation.md 6.5 KB
- references/facilitation-patterns.md 6.2 KB
- references/metrics-frameworks.md 7.4 KB
- references/patterns/ab-test.md 635 B
- references/patterns/backlog.md 1.1 KB
- references/patterns/dod-dor.md 907 B
- references/patterns/epic.md 884 B
- references/patterns/metrics.md 464 B
- references/patterns/prd.md 1.5 KB
- references/patterns/retro.md 2.2 KB
- references/patterns/roadmap.md 548 B
- references/patterns/sprint.md 935 B
- references/patterns/stakeholder.md 546 B
- references/patterns/story.md 1.4 KB
- references/patterns/velocity.md 401 B
- references/prioritization-frameworks.md 6.4 KB
- references/process-improvement.md 7.8 KB
- references/retro-trends.md 6.0 KB
- references/retrospective-formats.md 7.4 KB
- references/stakeholder-templates.md 5.5 KB
- references/user-stories.md 5.1 KB
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.
- 1mo ago First seen · 301 lines · 230 tokens per session scan A 5c9c888dd473
product-delivery is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 230 tokens to every session and 3,531 once invoked, about $0.0009 per session on Opus 5.5. 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 skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.