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/arcassystems/founderos/auditnpx skills add ARCASSystems/FounderOS --skill auditgit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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/arcassystems/founderos/audit)<a href="https://agentmods.dev/skills/arcassystems/founderos/audit"><img src="https://agentmods.dev/badge/skills/arcassystems/founderos/audit.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 | $0.00064 | $0.01012 |
| Opus 5 | $0.00032 | $0.00506 |
| Sonnet 5 | $0.00013 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
audit 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 3d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit
Runs on: reasoning - reads your files and reasons; any capable agent can run this.
This skill returns one Founder OS health report. It composes five checks that can also run on their own.
Pre-Flight
If core/identity.md does not exist, stop with: Founder OS not set up here. Run /founder-os:setup first.
Checks
Run all five checks. Sequential by default; parallel only if explicitly available.
Parallel path (preferred when the Agent tool is exposed in this Claude Code build): dispatch five sub-agents in a single message, one per check, each with a focused prompt that names the check and the expected output shape. Then merge the five results into the composite block.
Sequential path (fallback - applies if the Agent tool is not available, if a sub-agent fails, or if you are unsure): read skills/<check>/SKILL.md for each of the five checks below and apply its logic inline against the live OS. Mark the report parallel: unavailable.
For checks 4 and 5 there is no separate skill file - apply the rules below inline regardless of path.
- readiness-check - read
skills/readiness-check/SKILL.mdand apply. Returns score and next 3 moves. - lint - read
skills/lint/SKILL.mdand apply. Returns broken links, orphans, stale content, provenance gaps, possible contradictions. - wiki-build state - read
brain/relations.yamland report counts of curated edges and auto-generated wikilinks. Do NOT run wiki-build itself unless the user has approved the write at the gate above. Ifbrain/relations.yamldoes not exist, returnwiki: not initialised - run /founder-os:wiki-build to create it. - Brain staleness - count entries past
Decay after, flags older than Week 3, and rants inbrain/rants/older than 30 days whereprocessed: false. - Voice completeness - check whether
core/voice-profile.ymlandcore/brand-profile.ymlexist and have been filled past their template defaults.
Wiki Write Gate
Audit is read-only by default. wiki-build writes to brain/relations.yaml, so ask before running it:
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.
- 3d ago First seen · 88 lines · 64 tokens per session scan A 2eb36caa0bb5
audit is a skill published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 20d ago), licensed MIT. It adds 64 tokens to every session and 1,012 once invoked, about $0.0003 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
wiki-ingest
Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
markstream-vue2-cli
Integrate markstream-vue2 into a Vue 2 Vue CLI or Webpack 4 app. Use when Codex needs Webpack 4-friendly setup, CDN worker fallbacks for Mermaid or KaTeX, dist/index.css imports, Vue 2 composition-api shims, or code block choices limited to stream-diffs or plain .
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
publish-report
Publish local HTML, Markdown, or built static web projects with Pagecast as shareable public URLs. Use whenever Codex creates or finishes an .html, .htm, .md, .markdown, or static build output that a person could share (a report, plan, doc, dashboard, or analysis) — proactively offer to publish it without being asked…
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.