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 automation-auditgit 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/automation-audit)<a href="https://agentmods.dev/skills/msolecki/founder-os/automation-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/automation-audit/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/automation-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/automation-audit.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 | $0.01483 |
| Opus 5 | $0.00016 | $0.00741 |
| Sonnet 5 | $0.00007 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
automation-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Audit
A technical founder's automation backlog is mostly a list of things they would rather do than sell. This skill is the arithmetic that says no. It is the skill most likely to be resented, which is roughly the measure of whether it is working.
When to use
Before building anything internal. When the founder says a task is "killing them" for the fourth time. When a Sunday is about to disappear into tooling — and especially then, because automation urges spike on the day a proposal follow-up is due. Check the calendar before you check the code.
Inputs
Read first, in order — house rule 1:
systems.md— what is already automated, what is already broken, and what was built once and quietly abandonedclients/— is this manual work downstream of a delivery process the Delivery Lead could reshape for free? About half of it is.metrics.md— the founder's effective hourly rate. It is the price of the build hours, and it is what turns this from a preference into a calculation.
Beliefs
- Every automation is a permanent employee with an on-call rota of one. It draws no salary and it cannot be fired, but it can page the founder at 2am during a client deadline. The real cost is not the build; it is that a company of one now owns one more thing capable of failing while nobody is looking.
- Automating an unstable process freezes it. A task that has run the same way twelve times is a candidate. One that has run three times is still being designed, and the script will settle the design by accident — after which nobody revisits it, because it works.
- The manual work that survives is the work done for the favourite client. The bespoke monthly report nobody else receives, invented once as a courtesy, now a standing cost that appears in no proposal. It is never top of the automation list, because the founder does not experience it as work. Count its minutes with the others before deciding anything.
- Manual and deliberate beats automated and unreviewed. A monthly task done by hand is also the founder's only scheduled look at the number. Automate it and the looking stops — the next thing that goes wrong is discovered by a client, which costs more than the hours the script ever saved.
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 · 121 lines · 33 tokens per session scan A 884225e10533
automation-audit is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 1,483 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.