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 client-healthgit 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/client-health)<a href="https://agentmods.dev/skills/msolecki/founder-os/client-health"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/client-health/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/msolecki/founder-os/client-health"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/client-health.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 | $0.00031 | $0.01644 |
| Opus 5 | $0.00015 | $0.00822 |
| Sonnet 5 | $0.00006 | $0.00329 |
| Haiku 4.5 | $0.00003 | $0.00164 |
Grade A, and why
client-health 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Health
Engagements do not fail suddenly. They fail for six weeks and get discovered at renewal — the one moment when nothing can be repaired and the founder's only remaining move is a discount.
When to use
Monthly, per active engagement. Immediately when a client goes quiet mid-project or an invoice slips. Before every renewal conversation, never during one.
Inputs
Read first, in order — house rule 1:
clients/<client>.md— the engagement log: scope asks, hours, invoice dates, response timesmetrics.md— the invoice terms and this client's actual days-to-pay historypipeline.md— is a renewal or expansion pending? It changes what silence meansingestion-gate— the four signals are computed from dates in the log and need no gate. What the client said about them does: "cashflow is tight this quarter", "we're restructuring, it's not you". Those explain a red or excuse it, and which one they are is the gate's question, not this skill's.
Beliefs
- A client who has stopped complaining is not satisfied. Complaints are engagement. The quiet ones have already had the conversation about you internally and reached a conclusion nobody sent. Rising friction is a healthier signal than a relationship that has gone smooth.
- Health is a property of the deal's shape, not the client's personality. Most "difficult clients" were priced, scoped or sequenced badly at the start, and the same person on a better-shaped engagement would have been fine. This matters because personalities cannot be fixed and deals can.
- The founder is one of the signals, and they are not scoring themselves. A large share of failing engagements went quiet from the founder's end first: latency is bidirectional, and a client's tone frequently tracks the founder's own avoidance of them by about three weeks. Before scoring tone red, check who stopped replying.
- Renewal rewards the client having felt in control, not the work having been good. A client who cannot say what they got this month will not renew a project that went perfectly. The founder reads that as ingratitude; it is a reporting failure and it is fixable.
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.
- 9d ago First seen · 138 lines · 31 tokens per session scan A c023fcedae48
client-health is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 1,644 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.