meditate

Meditate

Autonomous Session Mode

When running non-interactively:

• Apply all high-confidence changes autonomously. For ambiguous or risky changes (brain file deletions, principle rewrites), file a todo instead.
• Commit only when the user authorizes it; follow the repository commit workflow.

Quality bar: A note earns its place by being high-signal (The agent would reliably get this wrong without it), high-frequency (comes up in most sessions or most tasks of a type), or high-impact (getting it wrong causes significant damage or wasted work). Everything else is noise. A lean, precise brain outperforms a comprehensive but bloated one.

Process

Track progress with the available planning tools or a short checklist.

1. Build snapshots

sh <skill-path>/scripts/snapshot.sh brain/ /tmp/brain-snapshot.md
sh <skill-path>/scripts/snapshot.sh .agents/skills/ /tmp/skills-snapshot.md

Files are delimited with === path/to/file.md === headers.

2. Auditor (blocking - its report feeds step 3)

Use an available general analysis subagent, or perform a bounded local review when delegation is unavailable. See references/agent-prompts.md § Auditor for the full prompt spec. Inputs: brain snapshot, auto-memory path, AGENTS.md path.

Audits brain notes, AGENTS.md, and auto-memory for staleness, redundancy, low-value content, verbosity, and orphans. Returns a categorized report.

Early-exit gate: If the auditor finds fewer than 3 actionable items, skip step 3 and go directly to step 4.

3. Reviewer (after auditor completes)

Use one available general analysis subagent, or continue locally when delegation is unavailable. See references/agent-prompts.md § Reviewer for the full prompt spec. Inputs: brain snapshot, skills snapshot, auditor report, brain/principles.md.

Combines three concerns in a single pass:

• Synthesis: Proposes missing Markdown links, flags principle tensions, suggests clarifications.
• Distillation: Identifies recurring patterns that reveal unstated principles. New principles must be (1) independent, (2) evidenced by 2+ notes, (3) actionable.
• Skill review: Cross-references skills against brain principles. Finds contradictions, missed structural enforcement, redundant instructions. Audits description frontmatters for context bloat.

4. Review reports

Present the user with a consolidated summary. See references/agent-prompts.md § Report Template for the format.

5. Route skill-specific learnings

Check all reports for findings that belong in skill files, not brain/. Update the skill's SKILL.md or references/ directly. Read the skill first to avoid duplication.

6. Apply changes

Apply all changes directly. The user reviews the diff.

• Outdated notes: Update or delete
• Redundant notes: Merge into the stronger note, delete the weaker
• Low-value notes: Delete
• Verbose notes: Condense in place
• New connections: Add file-relative Markdown links
• Tensions: Reword to clarify boundaries
• New principles: Only from the distillation section, only if genuinely independent. Write brain files and update brain/principles.md
• Merge principles: Look for principles that are subsets or specific applications of each other - merge the narrower into the broader and pick a name that captures the combined insight
• Bloated skill descriptions: Tighten frontmatter descriptions - cut what the agent can infer, keep only distinctive triggers and purpose
• AGENTS.md issues: Rewrite or delete
• Stale memories: Delete or rewrite

7. Housekeep

Maintain curated navigation through the brain skill; let hooks reconcile the root inventory.

Summary

## Meditate Summary
- Pruned: [N notes deleted, M condensed, K merged]
- Extracted: [N new principles, with one-line + evidence count each]
- Skill review: [N findings, M applied]
- Housekeep: [state files cleaned]