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 msolecki/founder-os --skill pricing-strategygit 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/pricing-strategy)<a href="https://agentmods.dev/skills/msolecki/founder-os/pricing-strategy"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/pricing-strategy.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 5.1 | $0.00031 | $0.01531 |
| Opus 5 | $0.00015 | $0.00766 |
| Sonnet 5 | $0.00006 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
pricing-strategy 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 7d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pricing Strategy
Hours are what the work costs the founder. They are not what the outcome is worth to the buyer, and the buyer has never once asked to see the timesheet.
The output of this skill that matters most is not the price. It is the floor — the number below which the answer is no — written down before a prospect is in the room. A floor invented during a negotiation is not a floor, it is a mood, and it always moves in the same direction.
When to use
After offer-design. Also before any proposal at a new number, when the founder
is about to discount to win a deal, and when they have not lost a deal on price
in six months.
Inputs
Read first, in order — house rule 1:
metrics.md— monthly burn including the founder's own pay, cash, and the effective rate on delivered work. Note the date; apply thecontext-loadstaleness rule and say the date out loud.offer.md— the offer, the outcome, and the real alternativeclients/— hours actually spent per engagement, including the unbilled onespipeline.md— what prospects have flinched at, and what they didn't
Beliefs
- Price is a claim about the buyer, not about the work. It changes who shows up long before it changes what anyone receives — which is why a rate rise arrives as a different clientele rather than as a better margin on the same one.
- Losing on price is cheap. Winning on price is what costs the quarter: a deal won on the number arrives with a client who bought a number, and they will manage the engagement like someone who bought a number.
- The founder's price is not low because they undervalue their work. It is low because a low price is an effective way of not being rejected, and it is working. That is why encouragement has never once moved it, and a floor written down before the room does.
Steps
- Compute the effective rate on the last three delivered engagements. Fee divided by hours actually spent, unbilled hours included. This is the only pricing fact you have; everything else is judgement.
- Check whether this is a pricing problem at all. If the effective rate is
below target but the list price is not, the leak is scope, not price. Raising
the price on an engagement that runs 38 hours over just raises the size of
the thing being overrun. Hand to the Delivery Lead —
scope-guard— before touching the number. - Set the floor from the numbers, not the nerve. Monthly burn (with founder
pay) divided by realistically billable days per month gives a day the
business cannot sell below. Then ask the question the founder is avoiding:
at what number would you rather have the free week? That is the floor.
Write it in
offer.mdwhere a future, more desperate version of the founder will read it. - Anchor on the buyer's alternative and the cost of not acting. What does the outcome pay them — in avoided hires, avoided downtime, a date they hit? Estimate it within an order of magnitude and label the estimate. If you cannot estimate it at all, you are pricing on hours by default, whatever the invoice says.
- Apply the flinch rule. If fewer than one in five qualified prospects flinches at the price, the price is too low — you are not being chosen, you are being defaulted to. Losing on price occasionally is the evidence the price is real.
- Build a concession ladder made of scope, never price. If you must move, remove a deliverable. Each rung: what comes out, what the new number is.
- Say what the discount teaches. A 20% discount to win one deal does not cost 20% of one deal. It sets the reference price for that client's renewal, their referral, and the next three prospects who talk to them. Name that cost out loud before the founder decides.
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.
- 7d ago First seen · 139 lines · 31 tokens per session scan A f4a3d3c92da8
pricing-strategy is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 1,531 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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…