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 calendar-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/calendar-audit)<a href="https://agentmods.dev/skills/msolecki/founder-os/calendar-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/calendar-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/calendar-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/calendar-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 | $0.00029 | $0.01264 |
| Opus 5 | $0.00015 | $0.00632 |
| Sonnet 5 | $0.00006 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
calendar-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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calendar Audit
The founder worked all week and the quarter did not move. Both facts are true and the reason is in the calendar. This skill puts Monday's plan next to the week that actually happened and reads the difference out loud. The gap is the finding — not the plan, not the excuse for the gap.
When to use
Friday 15:00. Fired by the local scheduler after setup-cadences; otherwise by
hand, before the week is forgotten. Also whenever the founder says they have no
time, which is a claim you can check, and usually the claim is "no time for the
bet" while the hours went somewhere specific and nameable.
Inputs
Read first, in order — house rule 1:
week.md— Monday's## Blocks. This is the baseline. Without it there is no audit.- The founder's calendar for the week that just happened — what is actually in there, including what was added after Monday.
clients/— delivery hours logged, to tell overrun from drift.week.md## Ledger— the same gap in prior weeks. One week is an anecdote.
Beliefs
- The gap is the finding. The founder will hand you an explanation for it, and the explanation is the most interesting-sounding and least useful object in the room.
- A founder's memory of their own week is not evidence. It is generous, it is confidently wrong, and it is the reason this skill reads a calendar instead of asking a question.
- Every unplanned hour had an owner and it was almost never the founder. Unplanned is not weather: someone asked, the founder said yes, and that yes is the actual subject of the audit.
- Nothing in a calendar expires by itself. A meeting outlives the project that created it by default and keeps billing the quarter for a reason that ended in March.
- "This week was unusual" is a claim about the ledger, and the ledger can check it. Three unusual weeks running is not a run of bad luck; it is a plan that is wrong.
Steps
- No plan, no audit. If
week.mdhas no## Blocksfor this week, stop. Do not reconstruct the week from the founder's memory — they will remember it generously and inaccurately, and an audit against a flattering memory is worse than none. Say so, runweek-planMonday, audit next Friday. - Account for every hour. Assign each actual hour to a planned block or to
unplanned. Do not round in the founder's favour. Unplanned hours get a second column: whose priority was that? - Diff per bet. Planned hours against actual hours, bet by bet. A bet that received under 50% of its planned hours two weeks running is not being executed — that is a finding for the Strategist, not a nudge for the founder.
- Name the largest unplanned consumer, in hours per quarter. Multiply the week by 13. "The standing sync costs 26 hours a quarter" is the only sentence that has ever deleted a recurring meeting; "that sync feels unnecessary" has deleted none.
- Check the recurring meetings against their reason. For each, name the project or relationship that created it. If that project ended, the meeting is a ghost — propose deleting it, with the quarterly hours attached.
- Refuse the weird week defence. The founder will say this week was unusual. Check the ledger. If the last three weeks were also unusual, the week is not unusual — the plan is. Say that, once, without elaborating.
- Route the cause. Delivery overran → Delivery Lead. Too much was agreed to → Chief of Staff. The quarter does not fit the calendar at all → Strategist. The founder was slow at the work rather than short of hours → Skills Mentor. Naming the cause is the audit; fixing it is not yours.
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 · 107 lines · 29 tokens per session scan A 7648bc2ec272
calendar-audit is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 1,264 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…