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 brainsparker/you.md --skill you-mdgit clone --depth 1 https://github.com/brainsparker/you.mdWrote 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/brainsparker/you.md/you-md)<a href="https://agentmods.dev/skills/brainsparker/you.md/you-md"><img src="https://agentmods.dev/badge/skills/brainsparker/you.md/you-md/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/brainsparker/you.md/you-md"><img src="https://agentmods.dev/badge/skills/brainsparker/you.md/you-md.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 | $0.00070 | $0.01338 |
| Opus 5.5 | $0.00028 | $0.00535 |
| Sonnet 5.5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
you-md 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
you.md
A you.md is a small markdown file describing a person: how they like to be communicated with, what they work on, what they care about, what to avoid. It is theirs, and it is meant to be read by any AI tool — not just this one.
You write the profile. The you.md server only validates, versions, and stores what you send it. It never infers anything about the user, so nothing lands in the profile unless you put it there.
When to use this
Trigger on requests like:
- "Create my you.md from what you know about me"
- "Make my you.md" / "Save what you know about me to you.md"
- "Create a portable profile from what you know about me"
- "Update my you.md with what you've learned about me"
- "Show me my profile" / "What's in my you.md?"
- "Export my you.md"
The user should never have to learn a command. Any natural phrasing of the above is the same request.
Creating a profile
- Synthesize first. Draw only on what you already know about this user from available context. Do not ask them to fill in a questionnaire; the point of the product is that you already know some of this.
- Write the complete markdown yourself using the template below.
- Call
youmd_create_profilewith that markdown. - Show the user the profile — the whole thing, in the conversation. Do not hide it behind a link or a summary. The conversation is the interface.
- Say what you left out and why, in one line: "I left out things that looked temporary or that I wasn't confident about."
- Offer the next moves: remove something, change something, add something, or export it.
If youmd_create_profile reports that a profile already exists, switch to the
update flow instead of overwriting.
Template
---
schema_version: "1.1"
privacy_level: "private"
source: "chatgpt"
---
# Me
## How I Think
## How I Communicate
## What I Do
## What I'm Working On
## What I'm Into
## Where I'm Headed
## Context
## Don't
Omit any section you have no real evidence for. An absent section is fine; an empty or padded one is worse than nothing. Write plain declarative sentences or short bullets — this file is read by other models, so clarity beats prose.
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.
- 1mo ago First seen · 153 lines · 70 tokens per session scan A a01a4fe61b01
you-md is a skill published in the GitHub repository brainsparker/you.md (2 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 1,338 once invoked, about $0.0003 per session on Opus 5.5. 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
memory-system
Design guidance for giving an AI a persistent memory system. It covers storing, finding, using, changing, and deleting information such as user preferences and project knowledge.
mnemex-skills
Use mnemex before implementing a significant code change. Mnemex is a local-first decision-integrity layer: it anchors a decision to code and reports whether that decision is still fresh.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…