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/proposal-draftnpx skills add msolecki/founder-os --skill proposal-draftgit clone --depth 1 https://github.com/msolecki/founder-osWhat 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 | $0.00040 | $0.02926 |
| Opus 5 | $0.00020 | $0.01463 |
| Sonnet 5 | $0.00008 | $0.00585 |
| Haiku 4.5 | $0.00004 | $0.00293 |
Grade A, and why
proposal-draft 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 3d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal Draft
Four things make a proposal: scope, price, exclusions, expiry. Founders write the first two beautifully and skip the last two, and then spend the project paying for it.
The exclusions are the point. They are not fine print and they are not
defensiveness — they are the scope baseline that scope-guard (Delivery Lead)
enforces in week five when the client asks for "one small thing". An exclusion
that is not written in this document does not exist. "We both understood that
wasn't included" has never once worked, on anyone, in the history of
professional services.
When to use
When a deal is qualified — amount named, decision-maker identified, trigger
real — and the next action is to propose. Not before capacity-check.
Inputs
Read first, in order — house rule 1:
-
pipeline.md— this deal: what they asked for, in their words, on the call -
voice.md—## Samples,## Tells,## Never,## Register. A proposal is the most formal thing the founder sends, and## Registersays by how much the formality shifts — it shifts from their baseline, not to a generic one. A founder who writes in three-sentence paragraphs does not become a management consultant on page one, and the buyer who liked them on the call is the person reading this. The prose sections are where this lands: the problem statement, "done means", and the consequence attached to each exclusion.If
## Samplesis empty, say so on the handoff — "no voice samples on record; this reads as a generic proposal document" — and hand the foundervoice-capture(Brand Editor). -
offer.md— the offer, the### Not includedlist, the price, and the floor. You copy from this file; you do not invent a number in it. -
clients/— the most important input. Every scope overrun that actually happened, and every hour delivered and never billed. This is where the real exclusions live. -
Delivery Lead's
capacity-check— the start date. You do not know what is free, and guessing commits the founder to work they cannot deliver.
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.
- 3d ago First seen · 233 lines · 40 tokens per session scan A c18aa33242f4
proposal-draft is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 2,926 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…