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.
git clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/commands/stefanoskarakasis/product-marketing-skills/proof-points)<a href="https://agentmods.dev/commands/stefanoskarakasis/product-marketing-skills/proof-points"><img src="https://agentmods.dev/badge/commands/stefanoskarakasis/product-marketing-skills/proof-points/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/commands/stefanoskarakasis/product-marketing-skills/proof-points"><img src="https://agentmods.dev/badge/commands/stefanoskarakasis/product-marketing-skills/proof-points.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 | $0.00000 | $0.00407 |
| Opus 5.5 | $0.00000 | $0.00163 |
| Sonnet 5.5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
proof-points 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 19d 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.
What it actually says
/pmm-positioning:proof-points -- Proof Points
Govern the evidentiary foundation of every claim your GTM copy makes — what's approved, what needs a source, and what's forbidden and why. Mines claim candidates out of existing sales decks, battlecards, and case studies, adds a new claim directly, checks one before it ships, or audits the existing registry for gaps. Deepens brain Section 6 in place, on confirmation.
Invocation
/pmm-positioning:proof-points Pull proof points out of this battlecard: [paste]
/pmm-positioning:proof-points Add: 89% retention rate, from our Q4 earnings
/pmm-positioning:proof-points Can I say "industry-leading" in this deck?
/pmm-positioning:proof-points Audit our proof points — anything stale or unsourced?
Workflow
Uses the proof-points skill. Loads brain Section 6 (current registry,
however thin) if present, classifies the request as Extract / Add / Verify
/ Audit. Extract mode mines claim-shaped statements out of pasted decks or
battlecards — every candidate starts flagged [NEEDS PROOF], even if the
source material cites its own source, since decks go stale. Add mode
requires a source for a directly-supplied claim (unsourced claims are
flagged, never silently approved) and documented approval-to-use for
every named customer quote. Then deepens brain Section 6 with the result
— showing the exact before/after first, writing only on confirmation.
Closes with a session log to /context/skill-sessions.md.
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.
- 19d ago First seen · 35 lines · 0 tokens per session scan A 30ecaca6e325
proof-points is a command published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. 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 2026-09-27.
Other commands, from other repositories
brief-me
Get briefed — loads your full memory, pulls live state from all connected tools, surfaces risks, staleness, upcoming milestones, and gives you a prioritized briefing so you're never starting blank.
design-ai-feature
Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes, cost modeling, and improvement flywheel.
competitive-intel
Run a competitive intelligence analysis — landscape mapping, battlecards, 7 Powers moat comparison, positioning gaps, and monitoring plan.
discover
Run a full discovery cycle — problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and OST mapping — from a rough idea to validated opportunity.
plan-launch
Plan a full go-to-market launch — positioning, messaging hierarchy, ICP definition, launch timeline, rollback plan, and post-launch measurement.
retro
Run a post-ship retrospective — measure outcomes vs. predictions, extract lessons, update memory, and feed insights back into the PM system.