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 mikeshu2001/personal-brain-builder --skill build-personal-braingit clone --depth 1 https://github.com/mikeshu2001/personal-brain-builderWrote 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/mikeshu2001/personal-brain-builder/build-personal-brain)<a href="https://agentmods.dev/skills/mikeshu2001/personal-brain-builder/build-personal-brain"><img src="https://agentmods.dev/badge/skills/mikeshu2001/personal-brain-builder/build-personal-brain/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/mikeshu2001/personal-brain-builder/build-personal-brain"><img src="https://agentmods.dev/badge/skills/mikeshu2001/personal-brain-builder/build-personal-brain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 153 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 447 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00081 | $0.04792 |
| Opus 5 | $0.00041 | $0.02396 |
| Sonnet 5 | $0.00016 | $0.00958 |
| Haiku 4.5 | $0.00008 | $0.00479 |
Grade A, and why
build-personal-brain 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Personal Brain
Build one durable personal memory without making the owner understand the implementation. Treat the downloaded builder, the owner's source material, and the generated memory as three separate things:
- the builder contains this skill, its references, templates, and control tool;
- source material remains read-only during the initial build;
- the generated memory lives in a separate owner-approved private directory.
Never create the generated memory inside this skill or inside the downloaded builder. Never copy personal knowledge back into this repository.
Speak to the owner
Use the owner's language. During onboarding, use ordinary words and one main question at a time. Explain the purpose, effect, and boundary of the next action before asking permission. Do not expose implementation terms such as Git, allowlist, frontmatter, runner, sentinel, schema, commit, or repository unless the owner asks for technical detail.
For a first run, read these files completely before replying:
references/plain-language.mdreferences/user-dialogue.mdreferences/safety-rules.mdreferences/state-machine.md
Use references/user-dialogue.md as a behavioral script, not as text to recite.
Adapt each message to what is already known and never repeat answered
questions.
Start or resume safely
On every invocation:
- Look only for a local
.personal-brain-pointer.json, an owner-provided memory path, or a state file inside a selected memory. - Do not inspect work folders while discovering prior progress.
- If exactly one pointer is found, show the exact separate memory location
and obtain permission to check saved progress there. Only then load its
work/setup/state.jsonand continue from its recorded state. Permission to read the downloaded builder does not permit opening the separate memory. - If multiple memories or mismatched identities are found, show a short choice and do not select one.
- If the state is damaged or unexpected memory changes exist, stop the affected action and explain the concrete issue.
- If no memory exists, begin the compatibility check and introduction.
What ships with it
35 files 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.
- agents/openai.yaml 219 B
- assets/brain-template/.brainignore 310 B
- assets/brain-template/.gitignore 262 B
- assets/brain-template/links/brain-index.md 460 B
- assets/brain-template/profile/owner.md 767 B
- assets/brain-template/START-HERE.md 1.0 KB
- assets/brain-template/system/brain-format.json 250 B
- assets/brain-template/system/conventions.md 2.8 KB
- assets/brain-template/system/runner-contract.md 3.5 KB
- assets/brain-template/system/runtime/README.md 570 B
- assets/brain-template/system/schema.md 4.4 KB
- assets/brain-template/system/statuses.md 1.4 KB
- assets/brain-template/system/templates/conflict.md 292 B
- assets/brain-template/system/templates/decision.md 196 B
- assets/brain-template/system/templates/entity.md 191 B
- assets/brain-template/system/templates/journal-entry.md 278 B
- assets/brain-template/system/templates/link.md 220 B
- assets/brain-template/system/templates/observation.md 140 B
- assets/brain-template/system/templates/person.md 185 B
- assets/brain-template/system/templates/project.md 291 B
- assets/brain-template/system/templates/rule.md 169 B
- assets/runner-pointer.md 702 B
- references/acceptance-tests.md 17 KB
- references/audit-protocol.md 22 KB
- references/connection-protocol.md 10 KB
- references/maintenance.md 11 KB
- references/memory-model.md 13 KB
- references/plain-language.md 13 KB
- references/safety-rules.md 21 KB
- references/state-machine.md 39 KB
- references/user-dialogue.md 52 KB
- scripts/brainctl.py 169 KB runs code
- scripts/card_engine.py 66 KB runs code
- scripts/portable_history.py 74 KB runs code
- scripts/state_control.py 64 KB runs code
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 · 482 lines · 81 tokens per session scan A 0a6e7ea20cc6
build-personal-brain is a skill published in the GitHub repository mikeshu2001/personal-brain-builder (29 stars, last pushed 8d ago), licensed MIT. It adds 81 tokens to every session and 4,792 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
edit-brain
How to add or edit knowledge in this brain — define doctypes, add or update entities, and correlate them with relationships. Use whenever the user asks to add/update knowledge, define a concept, record a learning, or link two things in the brain.
codex-memory-guard
Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory, compact HANDOFF checkpoints, PreCompact and compact-resume hooks, four-layer Markdown memory initialization, or memory workflow auditing.
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.