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 skills/matrixfounder/agentic-development/skill-product-handoffnpx skills add MatrixFounder/Agentic-development --skill skill-product-handoffgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote 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/matrixfounder/agentic-development/skill-product-handoff)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/skill-product-handoff"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/skill-product-handoff.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 | $0.00025 | $0.00582 |
| Opus 5 | $0.00013 | $0.00291 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
skill-product-handoff 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Handoff Protocol
1. Objective
To ensure that NO technical work begins until the Product Artifacts are Verified, Approved, and Compiled.
2. The Quality Gate
You MUST verify that the Product Director (p03) has signed off.
Gate Prerequisites
Before requesting sign-off, verify:
- Product Score: > 70/100 (from
skill-product-analysis). - Financials: Positive NPV & ROI > 2.0x (from
skill-product-solution-blueprint). - Backlog: Prioritized with WSJF.
Verification Command
python3 [skill_path]/scripts/verify_gate.py --file docs/product/APPROVED_BACKLOG.md
Note:
[skill_path]is the path to this skill (e.g..agent/skills/skill-product-handoff).
- Exit Code 0: GATE OPEN. Proceed.
- Exit Code 1: GATE CLOSED. Stop immediately.
Signing Command (For p03)
python3 [skill_path]/scripts/sign_off.py --file docs/product/APPROVED_BACKLOG.md
3. BRD Compilation
Once the gate is open, you MUST compile the scattered artifacts into a single BRD.md.
Compilation Command
python3 [skill_path]/scripts/compile_brd.py --market-file docs/product/MARKET_STRATEGY.md --vision-file docs/product/PRODUCT_VISION.md --blueprint-file docs/product/SOLUTION_BLUEPRINT.md --output-file docs/BRD.md
- Inputs:
MARKET_STRATEGY.md,PRODUCT_VISION.md,SOLUTION_BLUEPRINT.md. - Output:
docs/BRD.md.
4. Triggering Technical Phase
After the BRD is compiled, you initiate the Technical Phase.
Trigger Command
python3 [skill_path]/scripts/trigger_technical.py docs/BRD.md docs/TASK.md
- Effect: Creates the root
TASK.mdfor the Architect/Developer agents.
5. Workflow Integration
This skill is primarily used by the Orchestrator (p00) or the Handoff Workflow to accept the final output from p04.
6. Examples
- BRD:
examples/example_brd.md(Typical output structure). - Gate:
examples/example_approved_backlog.md(Showing valid Hash format).
What ships with it
8 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.
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.
- 4d ago First seen · 61 lines · 25 tokens per session scan A 52e2da59c317
skill-product-handoff is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 582 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 skills, from other repositories
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.