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 energy-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/energy-audit)<a href="https://agentmods.dev/skills/msolecki/founder-os/energy-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/energy-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/energy-audit"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/energy-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 | $0.01414 |
| Opus 5 | $0.00016 | $0.00707 |
| Sonnet 5 | $0.00007 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
energy-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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Energy Audit
Energy is calendar shape, not willpower: what the founder does, when, and in
what order. The workspace has been recording which blocks got finished and at
what hour for weeks now, and that record answers a question the founder cannot
answer from memory — which hours actually produce work, and which sequence
destroys them. The output is two lines in week.md that week-plan uses on
Monday to place deep work. That is the whole point of this skill.
When to use
Monthly, or when the pattern in calendar-audit is that the blocks were there
and the work still did not happen. That is not a scheduling failure — the hours
were booked — so the question moves to which hours they were.
Inputs
Read first, in order — house rule 1:
week.md— the## Ledgerand the## Audit. This is the record: planned against actual, week after week. It is the only evidence you have.reviews/daily/— the one thing committed each day, and whether it happened. Cross this against the hour it was blocked for.clients/— delivery hours, to see which weeks mixed sales and delivery.metrics.md— output that shipped, so "good week" means something checkable.
Beliefs
- The founder cannot answer "when do you work best" and the ledger can. Asked
directly, they will report an identity — "I'm a morning person" — and the
record will report a completion rate. When the two disagree, the number is
what
week-plangets. - A calendar is a claim and the audit is the evidence. A block on Tuesday says the founder intended to work at 14:00; only the ledger says whether anything finished. This skill reads the second thing and treats the first as a hypothesis.
- Founders misremember where the week went, in a consistent direction. The hours that hurt are recalled as longer and the hours that vanished are not recalled at all — which is why a shape reconstructed in conversation is worth less than no shape.
- Four weeks is the floor because three will produce a pattern. An invented
shape is worse than an empty one:
week-planwill build a quarter of blocks on it, and nothing in the workspace will ever contradict it. - A flat result is a finding, not a failure to look harder. The pressure to return a shape is exactly how a chronotype gets invented and then scheduled around for a year.
- The count of days off is an observation. What it means about a person is not
this skill's question and not this company's — read
## Guardrailsbefore you write the sentence after the number.
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 · 120 lines · 33 tokens per session scan A d1fa06058d5a
energy-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 1,414 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
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…