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 cafe-updategit 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/cafe-update)<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/cafe-update"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/cafe-update/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/cafe-update"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/cafe-update.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 | $0.00067 | $0.02795 |
| Opus 5 | $0.00034 | $0.01398 |
| Sonnet 5 | $0.00013 | $0.00559 |
| Haiku 4.5 | $0.00007 | $0.00280 |
Grade A, and why
Cafe Update 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 11d 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 — 230 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 cafe update crafting and practice interactively. Triggered by direct invocation or natural conversation.
Evaluate mode: Read a written update, stakeholder communication, or exec summary silently, score its cafe-update qualities, 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 written update, exec summary, or communication document. 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 — follows 5-Part Structure, audience-adapted, creates urgency for follow-up meeting
Dimensions to evaluate:
-
Messaging & communication — Does the update follow the 5-Part Cafe Update Structure (Context → Win → Insight → Ask → Close)? Does the Context reference something the LISTENER cares about (not what the PM cares about)? Is the Win specific and verifiable (named customer, quantified outcome)? Is it audience-adapted using the "What Would Get Them Fired?" test, or generic?
-
Stakeholder alignment — Does the Insight scale from one win to a systemic pattern? Is the Ask specific and bounded (not "let me know if you want to discuss")? Would it fit in 60 seconds? Does it position the PM as a strategic thinker or a feature reporter? Does it create a follow-up meeting or end the conversation?
Red flags to check:
- Feature report ("We just launched X")
- Generic update (same for all stakeholders, not adapted)
- Vague win ("Users are loving it" with no name or metric)
- No insight or scaling from one win to pattern
- No ask, or ask too big/vague ("Would you like to move forward?")
- Takes more than 60 seconds
- Opens with what PM built instead of what listener cares about
- No specific follow-up meeting created
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.
- 11d ago First seen · 230 lines · 67 tokens per session scan A b2f20c0b5e9b
Cafe Update Coach is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 2,795 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pm-data
A workflow for defining product metrics, tracking events, monitoring results, and planning data analysis.
domain
When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
session-cleanup
Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…