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 founder-os-doctorgit 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/founder-os-doctor)<a href="https://agentmods.dev/skills/msolecki/founder-os/founder-os-doctor"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/founder-os-doctor/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/founder-os-doctor"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/founder-os-doctor.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 | $0.00033 | $0.05987 |
| Opus 5 | $0.00016 | $0.02993 |
| Sonnet 5 | $0.00007 | $0.01197 |
| Haiku 4.5 | $0.00003 | $0.00599 |
Grade A, and why
founder-os-doctor 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS Doctor
The workspace is the company's memory, and every agent's advice is only as good as the state it read. Corrupt state does not announce itself. It produces confident, well-structured, wrong advice — which is strictly worse than no advice, because the founder acts on it.
This skill finds the rot. It reports first and repairs only what the founder confirms, because a doctor that silently fixes things is indistinguishable from the thing that broke them.
When to use
Monthly, and immediately after any of these:
- An agent said something that felt wrong. It usually read something stale.
- Founder OS updated. A release can declare a file, a directory or a section
the founder's workspace predates, and
founder-os-initscaffolds once and never runs again. The gateway repairs the two cheapest cases by itself — it creates a declared directory on the owner's first write, and it names a missing declared heading in every read — but nothing tells the founder the rest of the inventory drifted. That is this run. - The founder returns after two weeks away.
founder-os-initrefused to run because a workspace already exists.- The founder is about to report a problem with this package upstream —
see
## The shareable report, which is the only output of this skill that is meant to leave the machine, and leaves it in the founder's hands.
Inputs
references/ownership.yaml—workspace_files:is the expected inventory andsections:is the expected structure inside each flat file. Both are checks.- Every file in
$FOUNDER_OS_HOME, plus its last-modified date. The dates are half the diagnosis. $FOUNDER_OS_HOME/_local/, if it exists — the founder's local overlay, andreferences/extensibility.mdis its contract. This is the only validation the overlay ever gets.scripts/validate_package.pychecks the package in CI, on a machine that will never see a stranger's_local/, so every check that file's contract needs has to run here — weeks later, on real state, at a moment nobody chose. That is worse than build time and it is the only option available; say so in the report rather than implying the overlay was vetted.~/.founder-os/businesses.yaml, if it exists — the multi-business registry. It scopes the run: you doctor one workspace per run, the one resolved bycontext-loadstep 0, and the portfolio check below is the one place you look outside it. No registry, no portfolio check — a single-business install has nothing there to be sick.
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 Changed · +8 lines 125b7b1588a5
- 11d ago First seen · 274 lines · 33 tokens per session scan A 3e8492a4895d
founder-os-doctor is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 5,987 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.