Deep lookup in the project-brain vault. Use when the user asks about past work, decisions, or details from earlier sessions and the injected index isn't enough, or when explicitly invoked.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add vikasgrac/project-brain --skill recall --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Recall?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vikasgrac-recall)More formats (shields.io, HTML) on the badges page.
---
name: recall
description: Deep lookup in the project-brain vault. Use when the user asks about past work, decisions, or details from earlier sessions and the injected index isn't enough, or when explicitly invoked.
---
# Brain recall — deep lookup
The user's cross-project knowledge brain is a plain-Markdown vault. Resolve its location first:
`$BRAIN_DIR` env var if set, else `vault_path` in `~/.config/claude-brain/config.json`, else `~/claude-brain`. Call it `<vault>` below.
If `$BRAIN_READ_ALSO` is set, it names one or more additional vaults (colon-separated) to search **read-only** after `<vault>`. This is how a session that captures into its own vault — a local-model or experimental setup — still gets the benefit of the main brain's history. Never write to a `$BRAIN_READ_ALSO` vault: no file edits, no new notes, no `git commit`. Treat it strictly as reference, and say which vault a fact came from when you report it.
Perform a thorough, layered lookup for the topic in `$ARGUMENTS` (or the current conversation's open question if no arguments). Work down the layers, stopping as soon as the question is fully answered:
1. **Index**: read `<vault>/MEMORY.md` — identify which project(s)/topic(s) are relevant.
2. **Pages**: read the relevant `<vault>/projects/<name>.md` and/or `<vault>/topics/<name>.md`.
3. **Session notes**: if the page lacks detail, read recent `<vault>/sessions/<project>/*.md` notes (check `date:` frontmatter; newest first).
4. **Archive (episodic layer)**: for exact wording, commands, numbers, or anything the notes summarized away, grep the full transcripts: `rg -i "<terms>" <vault>/archive/<project>/` — then read the matching section of the hit file.
5. **Cross-project**: if the topic spans projects, repeat 2–4 for each; also `rg` across all of `<vault>/archive/` when unsure where something happened.
Rules:
- Never load whole directories — index first, then only the files the index/grep points to.
- Prefer `status: verified` content over `generated` when they disagree, and say so if they conflict.
- Report what you found AND where (file paths), so the user can follow up.
- If nothing is found, say so explicitly and suggest which project's archive is most likely to need a manual look.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!