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 BrennanJCollins/UnabatedPM-coaching --skill vision-synthesisgit clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coachingWrote 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/brennanjcollins/unabatedpm-coaching/vision-synthesis)<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/vision-synthesis"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/vision-synthesis/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/brennanjcollins/unabatedpm-coaching/vision-synthesis"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/vision-synthesis.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 | $0.00063 | $0.03540 |
| Opus 5.5 | $0.00025 | $0.01416 |
| Sonnet 5.5 | $0.00013 | $0.00708 |
| Haiku 4.5 | $0.00006 | $0.00354 |
Grade A, and why
Vision Synthesis Coach 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Modes
This skill operates in two modes:
Conversation mode (default): Coach the PM through the framework interactively. Triggered by direct invocation or natural conversation.
Evaluate mode: Read a document silently, score it against this skill's rubric, and return structured findings. No conversation, no questions — just assessment. Triggered by the /audit orchestrator.
Evaluate Mode Instructions
When invoked in evaluate mode, you receive a document and return a structured assessment. Do NOT coach. Do NOT ask questions. Read and score.
Score each dimension 1-5:
- 1 = Not present or fundamentally broken
- 2 = Attempted but significant gaps
- 3 = Competent but missing key elements
- 4 = Strong with minor improvements possible
- 5 = Exemplary — would pass senior PM review
Dimensions to evaluate:
- Vision, storytelling, & inspiration — Does the vision describe the WORLD that exists (not the product)? Does it pass the 4 quality tests (Boring, Clarity, Belief, Decision)?
Apply Vision Triangle + 4 Quality Tests to score:
- Vision Triangle complete: Customer Truth + Market Shift + Unique Capability = Vision
- Boring Test: Does it make you feel something, or is it marketing copy?
- Clarity Test: Can a new employee explain it?
- Belief Test: Ambitious enough to inspire, concrete enough to believe?
- Decision Test: Does it help you say NO to features?
Return format:
SKILL: Vision Synthesis
CATEGORIES SCORED:
- Vision, storytelling, & inspiration: [X]/5
Evidence: "[exact vision statement from document]"
Gap: [which 4-test failures — product-centric / metric-focused / borrowed / too vague?]
Upgrade: [single highest-leverage reframe]
VISION TRIANGLE STATUS:
- Customer Truth: [present/missing]
- Market Shift: [present/missing]
- Unique Capability: [present/missing]
4-TEST RESULTS:
- Boring Test: [Pass/Fail + why]
- Clarity Test: [Pass/Fail + why]
- Belief Test: [Pass/Fail + why]
- Decision Test: [Pass/Fail + why]
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 · 365 lines · 63 tokens per session scan A eadafb2b7579
Vision Synthesis Coach is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (5 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 3,540 once invoked, about $0.0003 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
pm-brand-motion
A guided process for defining a brand's motion style and making a logo animation demonstration.
pm-brainstorm
A guided brainstorming workflow for exploring a new product idea before detailed research or requirements work. It collects basic information about the product, users, and problem through staged questions.
pm-aarrr
A post-launch product-growth workflow based on AARRR: acquiring users, activating them, retaining them, earning revenue, and gaining referrals.
prompt-pe
Use when the user explicitly invokes /prompt-pe or explicitly asks to clarify, enhance, or rewrite a vague prompt Do NOT use for ordinary product-management requests; leave existing super-pm/start-super-pm routing unchanged.
pm-priority
A Chinese-language procedure for ranking several product requests when time or resources are limited. It supports scoring or grouping methods such as RICE, KANO, and MoSCoW to decide what should be done first.
pm-search
A workflow for collecting market research, competitor information, industry discussion, and compliance-policy data using an external search tool.