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 marcos-sponton/frameworks-as-skills --skill shreyas-doshigit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/skills/marcos-sponton/frameworks-as-skills/shreyas-doshi)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/shreyas-doshi"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/shreyas-doshi/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/marcos-sponton/frameworks-as-skills/shreyas-doshi"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/shreyas-doshi.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 | $0.00257 | $0.02336 |
| Opus 5.5 | $0.00103 | $0.00934 |
| Sonnet 5.5 | $0.00051 | $0.00467 |
| Haiku 4.5 | $0.00026 | $0.00234 |
Grade A, and why
shreyas-doshi 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shreyas Doshi's PM Frameworks
Shreyas Doshi is a product leader (former PM at Stripe, Twitter, Google, Yahoo -- Stripe's fourth PM, later its first PM manager) who has built one of the most widely-cited collections of product management frameworks through Twitter/X threads, his Substack newsletter, podcast appearances (including multiple episodes on Lenny's Podcast), and a Maven course on Product Sense. He does not have a published book; his body of work is distributed, evolving, and thread-native. This skill captures the full constellation of his frameworks plus their ongoing refinements.
When this skill activates
Use this skill when the user is:
- Trying to prioritize their work and figure out where to spend energy (LNO framework).
- Preparing for a product launch and wants to identify risks before they happen (pre-mortems with Tigers/Paper Tigers/Elephants).
- Wondering why they feel busy but unproductive, or why their impact reviews are disappointing.
- Experiencing team conflict that seems like an execution problem but might be something else.
- Evaluating whether to build or research first, and how to think about that tradeoff.
- Deciding what customer problems to solve and wants to avoid the Focusing Illusion.
- Hiring or evaluating PMs and wants a framework for thinking about types and agency.
- Trying to communicate more effectively with executives vs. team members.
- Developing product sense or taste as a PM skill.
- Asking career questions about PM growth, what to focus on, or how to develop as a leader.
Do NOT use this skill when:
- The user wants a formal strategic choice cascade (Where to Play / How to Win) -- that's Roger Martin's Playing to Win territory. Shreyas operates at the PM/team level, not the corporate strategy level.
- The user needs a structured customer discovery method with interviews and opportunity trees -- that's Teresa Torres's Continuous Discovery Habits. Shreyas's CPSR complements CDH but doesn't replace it.
- The user is building a full organizational strategy document. Shreyas's frameworks are mental models for practitioners, not strategy architecture.
- The user wants a product development process or methodology (agile, Shape Up, etc.). Shreyas explicitly values judgment over process.
What ships with it
12 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.
- evals/evals.json 6.7 KB
- examples/.gitkeep 0 B
- README.md 5.8 KB
- references/applications.md 8.4 KB
- references/author-live-sources.md 6.9 KB
- references/examples.md 9.8 KB
- references/heuristics.md 8.8 KB
- references/method.md 17 KB
- references/post-book.md 10.0 KB
- references/prompts.md 5.8 KB
- references/sources.md 7.4 KB
- references/voice-and-tone.md 6.3 KB
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 · 95 lines · 257 tokens per session scan A 170ff42ad138
shreyas-doshi is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 257 tokens to every session and 2,336 once invoked, about $0.0010 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
book-club
A structured workflow for running a book club, covering book selection, scheduling, preparation, discussion, and planning the next meeting.
product-launch-retail
A documented workflow for taking a new product from research and pricing through listing, sales, and an initial review. It uses shared templates, task records, and sales data files.
cc-skill-project-guidelines-example
Project Guidelines Skill (Example).
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
report
Activity report from total-agent-memory for a project and period. Use when the user types /report or asks "report for today", "what did we do this week", "weekly / monthly summary", "status report", "retro for project X", "all-time report", "report for last week", or a report for a department or the whole company on…
ralph-linear
Fetch Linear tickets and build them with ralph-starter.