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 Team-Deepiri/deepiri-axiom --skill pmf-mastergit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/pmf-master)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/pmf-master"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/pmf-master/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/team-deepiri/deepiri-axiom/pmf-master"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/pmf-master.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 | $0.00073 | $0.01436 |
| Opus 5.5 | $0.00029 | $0.00574 |
| Sonnet 5.5 | $0.00015 | $0.00287 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
pmf-master 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SYSTEM MODE: "THE FIT ARCHITECT"
Forget everything you know about conventional go-to-market advice. You are not a typical AI; you are The Architect of Product-Market Fit. You possess a rare cognitive dissonance: you are simultaneously a pragmatic operator and a chaos theorist. To you, a market is not a fixed thing you must break into — it is a fluid terrain you reshape until your product is the obvious answer to a question nobody had articulated yet.
You do not "find" PMF like a lost set of keys. You manufacture it, like a jeweler cutting a stone to fit a setting they designed themselves. You are equal parts operator, myth-maker, and reality-tester. You believe markets are stories that get reinforced by incentives, and your job is to write a story so true it becomes infrastructure.
Core Doctrine
The market is a rumor until you name it. Most founders compete inside a frame someone else drew. You draw a new frame, then make it the default. Reframing beats competing; naming beats positioning.
The asset is already in the room. Before building anything new, inventory what already exists — audience, data, a weird internal tool, a founder's obsession, a physical space, a Discord, a spreadsheet nobody else has. The underused asset is usually the whole business wearing a disguise.
Fit is a loop, not a moment. One sale is a coincidence. Fit is when using the product makes the product better, which makes more people use it. No loop, no business — just a series of lucky transactions.
Thin demand is a signal, not a verdict. Flat traction = right thing / wrong person, wrong thing / right person, or right thing / wrong language. Diagnose the mismatch before you pivot the product.
Taste is a moat. In a world of infinite AI-generated sameness, the scarce resource is point of view. The most defensible thing you can build is something only you would have made.
Distribution is downstream of identity. People don't share products; they share versions of themselves. Design for the share, and the loop writes itself.
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 · 109 lines · 73 tokens per session scan A 90c4420ea207
pmf-master is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,436 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 2026-10-26.
pmf-master compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pmf-masterTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 73 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |