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 agentmods add skills/msolecki/founder-os/premortemnpx skills add msolecki/founder-os --skill premortemgit clone --depth 1 https://github.com/msolecki/founder-osWrote 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/msolecki/founder-os/premortem)<a href="https://agentmods.dev/skills/msolecki/founder-os/premortem"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/premortem.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01400 |
| Opus 5 | $0.00015 | $0.00700 |
| Sonnet 5 | $0.00006 | $0.00280 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
premortem 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premortem
It is six months from now. This failed. Not "might have" — did.
The tense is the technique. Asked what might go wrong, a founder produces a risk register: vague, balanced, and hedged, because part of them is still defending the plan while listing its flaws. Told the thing is already dead and asked for the coroner's account, the same founder produces specific causes with dates in them. Same information, same person. The difference is that the second question does not let them argue.
When to use
Before commitment, on anything hard to reverse — the bet-sizing runway rule
routes bet-the-company moves here automatically.
While the answer can still change the plan. If the decision is already made and the premortem cannot alter it, do not run it: it becomes reassurance theatre, and its only product is a story the founder can tell later about how they knew.
Inputs
Read first — house rule 1:
- The plan, and its judgement date
goals.md— what else is running, competing for the same foundermetrics.md— the numbers the story will have to breakreviews/weekly/— the record of how this founder's plans have actually failed before. The boring cause is already in there, in writing.clients/— revenue concentration, if delivery is in the path
Beliefs
- The tense is doing the work, not the imagination. "Might fail" produces a balanced risk register, because half the founder is still defending the plan while listing its flaws; "did fail" produces causes with months attached. Same person, same information — so a slide back into the conditional is not a wording slip, it is the exercise switching itself off.
- Founders premortem the exciting death and die of the boring one, and the reason is not a failure of imagination: the competitor shipping first is nobody's fault. Getting busy is. A story is only useful once it names a cause the founder is standing in.
- Count the live bets in
goals.mdthat need the same single pair of hands. Above three, stop investigating the market — the story is already written, the cause is attention, and the only open question is which of them dies first. - A risk register is how a founder imagines failure without thinking about it, and it leaves them feeling rigorous, which is the product it actually delivers. Having pictured the death is not a defence against it. The tripwire is, and it is the only line here that will still exist in month five.
What ships with it
1 file 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.
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.
- 5d ago First seen · 120 lines · 30 tokens per session scan A fba4e0456d06
premortem is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,400 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…