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 prepforeverything/prepkit-product --skill product-facilitationgit clone --depth 1 https://github.com/prepforeverything/prepkit-productWrote 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/prepforeverything/prepkit-product/product-facilitation)<a href="https://agentmods.dev/skills/prepforeverything/prepkit-product/product-facilitation"><img src="https://agentmods.dev/badge/skills/prepforeverything/prepkit-product/product-facilitation.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 5.1 | $0.00055 | $0.02718 |
| Opus 5 | $0.00028 | $0.01359 |
| Sonnet 5 | $0.00011 | $0.00544 |
| Haiku 4.5 | $0.00006 | $0.00272 |
Grade A, and why
product-facilitation 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 6d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone Mode: This skill is part of the prepkit-product plugin.
spec/product-context.mdis optional — provide context inline or create one from the template.- Output paths (
research/,reports/) are relative to your current working directory.- Facilitation routing is advisory — invoke any skill directly.
docs/product-foundation.mdis optional — the skill works without it.- Routing decisions are advisory in standalone mode, not authoritative.
Product Facilitation
Use this as a process skill. Activate alongside any product domain skill or workflow.
Goal:
- drive structured questioning so product work is grounded in evidence, not intuition
- manage shared product context across discovery, research design, specification, and prioritization
- act as the sole routing authority for next-step decisions
Routing Authority
product-facilitation decides the next move: research, PRD, experiment, defer, or reject.
Authority split:
product-facilitation- chooses the route
- owns backward routing when upstream thinking is missing
- records route rationale when an artifact or shared-state update needs it
- domain skills
- diagnose evidence quality, readiness, or tradeoff quality
- may emit advisory next-step labels
- do not independently choose the route
- workflows
- define checkpoints, inputs, and artifact sequencing
- invoke facilitation at decision points
- do not embed competing route logic
If diagnosis and workflow expectations conflict, choose the safer backward route.
Routing Decision Tree
- Is the problem statement clear and evidence-backed?
- No → route to
research(discovery or validation) - Yes → continue
- No → route to
- Has the opportunity been mapped and a pursue decision made?
- No → route to
product-opportunity-mapping - Yes → continue
- No → route to
- Is the evidence quality
patternor stronger?- No → route to
product-validationfor cheapest next evidence move - Yes → continue
- No → route to
- Are success metrics defined with baselines?
- No → route to
product-metrics-analysis - Yes → continue
- No → route to
- Is the team ready to specify scope?
- Yes → route to
PRD - No, needs experiment → route to
experiment - No, not worth pursuing → route to
rejectwith rationale - No, not now → route to
deferwith revisit trigger
- Yes → route to
What ships with it
3 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.
- 6d ago First seen · 204 lines · 55 tokens per session scan A bd16d75b54f1
product-facilitation is a skill published in the GitHub repository prepforeverything/prepkit-product (2 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 2,718 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.