Audit and evolve the brain vault — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers: /flux:meditate, "meditate", "audit the brain".
From fluxnpx claudepluginhub nairon-ai/flux --plugin fluxThis skill uses the workspace's default tool permissions.
references/agents.mdscripts/snapshot.shDesigns and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Quality bar: A note earns its place by being high-signal (Claude 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.
Adapted from brainmaxxing by @poteto.
On entry, set the session phase:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL session-phase set meditate
On completion, reset:
$FLUXCTL session-phase set idle
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
sh "$PLUGIN_ROOT/skills/flux-meditate/scripts/snapshot.sh" .flux/brain/ /tmp/brain-snapshot.md
sh "$PLUGIN_ROOT/skills/flux-meditate/scripts/snapshot.sh" skills/ /tmp/skills-snapshot.md
Files are delimited with === path/to/file.md === headers. Also locate the auto-memory directory (~/.claude/projects/<project>/memory/).
Spawn general subagent. See references/agents.md for the full prompt spec. Inputs: brain snapshot, auto-memory path, CLAUDE.md path.
Audits brain notes, CLAUDE.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.
Spawn one general subagent. See references/agents.md for the full prompt spec. Inputs: brain snapshot, skills snapshot, auditor report, .flux/brain/principles.md.
Combines three concerns in a single pass:
Present the user with a consolidated summary. See references/agents.md for the report format.
Check all reports for findings that belong in skill files, not .flux/brain/. Update the skill's SKILL.md or references/ directly. Read the skill first to avoid duplication.
Apply all changes directly. The user reviews the diff.
[[wikilinks]].flux/brain/principles.mdIf .flux/brain/business/ exists, audit it alongside the brain vault:
ls .flux/brain/business/*.md 2>/dev/null
If business context files exist:
billing.md) reference systems or decisions that are outdated. Update or prune.Present business context findings alongside the brain audit report. Apply changes with user approval.
Use meditate as the periodic correction loop for slop creep.
Review recent pitfalls, principles, and changed architecture notes for:
If the same forecast miss appears 2+ times, prefer structural encoding over prose:
Update .flux/brain/index.md for any files added or removed. Also update .flux/brain/business/index.md if business context files were added, removed, or renamed.
Update meditate timestamp so the session health check knows when this last ran:
mkdir -p "$HOME/.flux"
echo "$(date -u +%Y-%m-%dT%H:%M:%SZ)" > "$HOME/.flux/last_meditate"
## 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]