원클릭으로
brain
// Read/write the docs/ vault — this project's persistent memory. Use for any task that persists knowledge: reflection, planning, gotchas, principles, or direct edits. Triggers: docs/ modifications, "add to docs", "remember this".
// Read/write the docs/ vault — this project's persistent memory. Use for any task that persists knowledge: reflection, planning, gotchas, principles, or direct edits. Triggers: docs/ modifications, "add to docs", "remember this".
Turn a rough feature request into a concrete spec file at `specs/pending/<slug>.md`. Read the codebase first, then ask the user targeted questions, then write the spec. Use when the user says "design a spec", "spec this out", "/design-spec", or hands you a feature idea that needs to become a concrete spec before implementation starts.
Audit and evolve docs/ — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers: "meditate", "audit the docs".
Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing docs/. Triggers: "ruminate", "mine my history".
Produces a single-file interactive HTML explainer (dark theme, embedded React demos via CDN) by editing a self-contained template in place, written in Josh Comeau's conversational voice. Use when the user asks for an "interactive guide", "blog post explainer", "Josh Comeau style writeup", "visual deep-dive", "make this visual", or wants to turn a technical topic into a learning page with playable demos.
Reflect on the conversation and update docs/. Use when wrapping up, after mistakes or corrections, or when significant codebase knowledge was gained. Complements the automatic Stop-hook reflection (`.claude/hooks/docs-reflection.sh`) — invoke this manually for a deeper pass. Triggers: "reflect", "remember this".
| name | brain |
| description | Read/write the docs/ vault — this project's persistent memory. Use for any task that persists knowledge: reflection, planning, gotchas, principles, or direct edits. Triggers: docs/ modifications, "add to docs", "remember this". |
In this repo the persistent-memory vault is docs/. It doubles as the project wiki and the agent's long-term memory.
The brain is the foundation of the entire workflow — every agent, skill, and session reads it. Low-quality or speculative content degrades everything downstream. Before adding anything, ask: "Does this genuinely improve how the system operates?" If the answer isn't a clear yes, don't write it.
Read docs/index.md first. Then read the relevant entrypoint for your topic:
docs/principles.md for principlesdocs/plans/index.md for active or past plansdocs/patterns/effect-ai-gotchas.md for @effect/ai-specific gotchasdocs/guides/ for how-to recipesFor directories without a dedicated index file, scan nearby files directly and edit an existing note when possible.
docs/
├── index.md <- curated wiki landing page (manually maintained, NEVER auto-rewritten)
├── architecture.md <- the three layers, dataflow
├── tooling.md <- stack, check pipeline
├── testing-strategy.md <- pyramid
├── backlog.md <- known follow-ups
├── principles.md <- index for principles/ (auto-rebuilt)
├── principles/ <- engineering and design principles (one per file)
├── plans/ <- phased implementation plans
│ └── index.md <- auto-rebuilt
├── guides/ <- how-to recipes (adding-a-tool, testing)
├── patterns/ <- gotchas, conventions (effect-ai-gotchas)
└── stories/ <- learning narratives / journals
Rules:
docs/patterns/anthropic-rate-limits.md, not a mega-file.docs/index.md is the curated root — every section should be reachable from it. Do not rewrite it programmatically.docs/principles.md and docs/plans/index.md are auto-rebuilt by the PostToolUse hook. Don't hand-edit them — just add or remove files in the directory and the hook regenerates the index.effect-ai-gotchas.md.Format: [[section/file-name]]. Resolution order: same directory, then relative path, then vault root. Heading anchors ([[file#heading]]) are stripped during resolution.
# Title. No frontmatter on memory notes.If you added or removed a file in docs/principles/ or docs/plans/, the auto-index hook will rebuild the matching index. For other directories, update docs/index.md by hand if the new entry deserves a top-level mention.
Ask: "Would I include this in a prompt for a different task?"
docs/. It's durable knowledge.docs/backlog.md.repos/ content makes a doc redundant, link to the source file and delete the doc.