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-initgit 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-init)<a href="https://agentmods.dev/skills/msolecki/founder-os/founder-os-init"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/founder-os-init.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 | $0.00028 | $0.04992 |
| Opus 5 | $0.00014 | $0.02496 |
| Sonnet 5 | $0.00006 | $0.00998 |
| Haiku 4.5 | $0.00003 | $0.00499 |
Grade A, and why
founder-os-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS Init
This is the one resumable path from an installed package to a useful first daily brief. It runs as the Chief of Staff. It orchestrates the owner agents; it does not borrow their files or call a scaffold an activation.
Activation exists only when a valid brief has been persisted at
reviews/daily/YYYY-MM-DD.md in the workspace resolved at preflight. Until
then the workspace is incomplete and the next /founder-os-init continues it.
When to use
Run immediately after install, after moving FOUNDER_OS_HOME, or to resume an
interrupted first run. Do not use it to refresh an activated workspace; that is
/founder-os-doctor.
Start with Stage 0. Do not ask whether the founder is ready and do not mutate a workspace before preflight succeeds.
Inputs
references/ownership.yaml— the only source for scaffold paths, headings and owners.references/multi-business.mdand~/.founder-os/businesses.yaml, when the registry exists.$FOUNDER_OS_HOME, default./founder-os/.- the canonical Founder OS context injected into this session;
- existing workspace files and
reviews/daily/, read before any question.
Shared sibling request
Every owner transition returns one request to the main thread with exactly
role, workflow, workspace_id, correlation_id, handoff, and
expected_persistence. It carries one bounded handoff of at most 4096 UTF-8
bytes. The main thread passes that carried answer unchanged; it validates and
executes the request, while this workflow does not execute another role. Native
and generic execution both use the byte-identical packaged role under
references/orchestration.md.
Stage 0 — Preflight
Stage 0 is read-only. Finish every check before the first workspace write:
- Confirm the plugin manifest,
CLAUDE.md,references/house-rules.md,references/ownership.yaml,references/multi-business.mdand every downstream skill named below exist in the installed package. - Before normal target resolution, read an explicit resume tuple from the
invocation when one was supplied. It is complete only when it names the
exact recorded
FOUNDER_OS_HOME, business slug and resolved workspace path; a partial tuple stops instead of being guessed. - Resolve the target using the resume-resolution table below. Treat the
resulting path,
FOUNDER_OS_HOMEand business slug as one frozen resolved workspace tuple for the entire run. - Validate the registry without rewriting it. A second-business request
follows
references/multi-business.md; an ambiguous or invalid slug stops. - Check from filesystem metadata that the target or its nearest existing parent is writable. Do not create a probe file.
- Confirm the canonical context is present and carries
CLAUDE.md, the house rules, ownership map and resolved workspace. - Apply the daily-review validity invariant: in this resolved workspace,
a candidate
reviews/daily/YYYY-MM-DD.mdis valid only when it contains the headings declared forreviews/daily/byreferences/ownership.yaml, with a non-empty## The one thingand## The trade. Stage 6 uses this exact invariant again; there is no weaker activation check. - If the selected workspace's
decisions/*-founder-os-installed.mdalready carries a target checkpoint, compare itsFOUNDER_OS_HOME, business slug and resolved path with the selected tuple. Any mismatch outside the confirmed-relocation case stops before a read or write outside the selected workspace. - Read the target's
charter.md, owned outputs andreviews/daily/, then classify exactly one activation state:
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 · 381 lines · 28 tokens per session scan A 8b03f48c7945
founder-os-init is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 4,992 once invoked, about $0.0001 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…