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/rate-raisenpx skills add msolecki/founder-os --skill rate-raisegit 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/rate-raise)<a href="https://agentmods.dev/skills/msolecki/founder-os/rate-raise"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/rate-raise.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 | $0.00038 | $0.02007 |
| Opus 5 | $0.00019 | $0.01004 |
| Sonnet 5 | $0.00008 | $0.00401 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
rate-raise 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 6d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rate Raise
Every founder intends to raise their rates. The intention was never the obstacle. The obstacle is a fear with no number attached — how many clients leave? — and this skill puts the number on it. The number is usually startling enough to make the raise happen the same week.
When to use
When profitability-analysis shows the effective rate below target for two
consecutive quarters. When the win rate is too high. At the renewal of any client
in the bottom quartile. Not when the founder feels brave — bravery is not a
trigger, and it evaporates somewhere between deciding and sending.
Inputs
Read first, in order — house rule 1:
metrics.md— the per-client effective-rate table fromprofitability-analysis, the target rate, collected revenueclients/— thedelivery-retrovariances: where the estimate broke, and whypipeline.md— the win rate on proposals sent in the last two quartersoffer.md— what the Positioning Advisor says the offer is worth
Beliefs
- The rate is not a verdict on the founder, and treating it as one is what makes the conversation hard. It is a number that either funds the business or does not. On the other side of the email it is a line item next to three other line items, read by someone who will spend ninety seconds on it.
- Clients do not leave over a rate. They leave over a rate plus a doubt they already had. A raise reveals the relationship; it does not cause the exit. Finding out which relationships were already gone is worth the raise on its own, and it is information available no other way.
- The client the founder is most afraid of losing is the one to raise first. The fear is a fact about the founder's dependence, not about that client's value — and dependence is exactly the thing a rate raise exists to test. Raising everyone except them is not a raise; it is a confession, and next quarter's table will say so.
- Raising is faster than finding, and founders do it in the wrong order. The raise is available this week, from the desk, with no pipeline and no travel. A replacement client is sixty days and a pile of unpaid sales hours away. Founders pick the slow lever because it involves no confrontation.
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.
- 6d ago First seen · 158 lines · 38 tokens per session scan A 5f07803cca13
rate-raise is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 2,007 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
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.