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 annual-reviewgit 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/annual-review)<a href="https://agentmods.dev/skills/msolecki/founder-os/annual-review"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/annual-review/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/annual-review"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/annual-review.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 | $0.01443 |
| Opus 5 | $0.00015 | $0.00722 |
| Sonnet 5 | $0.00006 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
annual-review 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annual Review
Everyone reviews the year's results. The results are mostly luck, market, and
one client who happened to renew. What compounds is the quality of the
judgments, and the only place those are recorded before the outcome was known is
decisions/.
This is the one review that scores the reasoning. It is the reason house rule 3 exists at all — twelve months of logged decisions with falsifiers is an asset nobody else in a company of one has, and this skill is what cashes it.
When to use
Once a year, in the same week as Q4 quarterly-planning — and before it, so the
year's rules are available when next year's bets are chosen.
Inputs
Read first — house rule 1:
decisions/— every entry from the last twelve months. This is the review. Everything else is context.metrics.md— the numbers that settle whether each falsifier firedreviews/monthly/— used for exactly one thing, in step 4: checking whether the empty months were actually empty
Do not read the year's reviews/weekly/. They record what happened, which is
what this skill is deliberately not scoring.
Beliefs
- Hindsight is not extra information about a decision, it is different
information, and it is inadmissible here. The only fair judge of a call is what
was knowable on the day it was made, which is why this review reads
decisions/and not the year's results. - Nobody can remember what they believed before they knew the answer. This is not a failing of this founder; it is a property of people, and it is the entire reason the log exists. Memory is not an input to this review, however vivid.
- Success teaches the wrong lesson more reliably than failure does. A bad call that paid gets repeated, gets called instinct, and is invisible to every review that scores outcomes — including every review the founder has ever run on themselves.
- Most of what the founder is proudest of this year was variance, and so was most of what they are ashamed of. This review exists to find the thin residue that was actually judgment, and it will be a smaller pile than either of the other two.
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.
- 10d ago First seen · 128 lines · 29 tokens per session scan A 17e1b742fc3e
annual-review is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,443 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…