agentleFS
jzhao234jzhao234/big-brain/skills/codex/brain/SKILL.md

brain

Skill1 starsChanged 31 days agoMITView on GitHub

Orient from the user's Big Brain vault and stay brain-aware during ongoing work. Use when the user asks what they are working on, what is overdue, to catch them up, to zoom into a project, or explicitly invokes $brain.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run big-brain doctor only when health has not been checked recently or the user asks.

    line 20
  2. Distinctive:

    Before ending, verify that meaningful work from the session is reflected in the vault.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brain-aware work

Big Brain is the user's shared external memory. Resolve the vault through the big-brain CLI (BIG_BRAIN_VAULT, an explicit --vault, or the nearest brain.config.json); do not hardcode a path. Use Big Brain MCP tools when they are actually available, otherwise use the CLI and ordinary filesystem reads.

Orient

With no named topic:

  1. Run big-brain status.
  2. Report one-screen BLUF: active projects and next tasks, overdue/due-soon work, and inbox count when nonzero. Skip empty sections.
  3. Run big-brain doctor only when health has not been checked recently or the user asks; surface warnings, not routine clean output.

With a named project/topic, run big-brain show <topic>, falling back to big-brain search <topic>. Summarize the goal, status, open tasks, blockers, and latest log entries, then continue with the user's requested work.

Stay brain-aware

For the rest of the session, keep durable state current as work produces it:

  • decisions, progress, or failures → daily log and the relevant project log;
  • new multi-step commitment → project;
  • new action → task on the matching project;
  • completed action → mark its existing task done;
  • durable fact with no obvious home → capture or linked reference/note.

Routine append-only logs and captures are authorized when the user invoked this skill. Ask before rewriting, consolidating, archiving, or changing project status unless the user already requested that operation. Preserve vault frontmatter, area, work tags, tasks, and wikilinks. Never store credentials, tokens, private keys, or unredacted sensitive datasets.

Big Brain may auto-commit and auto-push writes. Treat a CLI write as an external mutation: describe it briefly in commentary and do not issue duplicate git commits afterward. If editing files directly because the CLI lacks the needed operation, inspect the vault's git config and leave a clean, synced repository only when the user authorized saving/syncing.

Before ending, verify that meaningful work from the session is reflected in the vault. Tell the user in one line what was recorded.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.