agentleFS
Sign inStart free
BuddhiliveBuddhilive/buddhi-cli/.agents/skills/remember/SKILL.md

remember

Skill1 starsChanged 13 days agoMITView on GitHub

Explicitly capture a user-stated preference, project convention, technical decision, or piece of feedback into an OKF v0.2 concept node and sync the memory index. Use when preserving persistent context with /remember.

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation, agentica-infrastructure and 10 more.

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.

The file

Create a free account to mount
Files
SKILL.md

/remember

$ARGUMENTS

Explicit, user-invocable capture of durable project knowledge into an atomic Google Open Knowledge Format (OKF v0.2) concept node under .agents/memory/, with automatic indexing into MEMORY.md.

Steps

  1. Take the content to remember from $ARGUMENTS. If ambiguous, ask the user to clarify.
  2. Classify into an OKF kind: decision, convention, preference, or feedback.
  3. Identify any source code anchors (path/file.py#L1-L20) or path glob patterns (src/api/**/*.py) that ground this knowledge.
  4. Execute buddhi memory add via CLI or call buddhi_memory(action="remember", ...):
    • Sets YAML frontmatter (id, kind, title, summary, status: stable, confidence: verified, paths, sources).
    • Computes SHA-256 content_hash for cited sources.
    • Saves atomic Markdown file under .agents/memory/<topic>/<slug>.md.
    • Rebuilds <topic>/index.md and updates root MEMORY.md within the 200-line budget.
    • Logs mutation into .agents/memory/log.md.
  5. Confirm back to the user the created concept ID, file path, and summary 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.

Check your setup, free