What is use-crystallized-brain?

A retrieval guide for a curated knowledge collection, called a crystallized brain, that stores domain principles and supporting documents.

Use it to bootstrap a domain, search for relevant files, expand a question with ranked sources, or retrieve one specific document.

It helps retrieve only the relevant guidance instead of loading an entire knowledge base into the working context.

use-crystallized-brain — Skill for Claude Code and Codex by bcharleson

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/bcharleson/crystallized-intelligence

agentmods

npx agentmods add skills/bcharleson/crystallized-intelligence/use-crystallized-brain

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bcharleson/crystallized-intelligence/use-crystallized-brain.svg)](https://agentmods.dev/skills/bcharleson/crystallized-intelligence/use-crystallized-brain)

Your own site

<a href="https://agentmods.dev/skills/bcharleson/crystallized-intelligence/use-crystallized-brain"><img src="https://agentmods.dev/badge/skills/bcharleson/crystallized-intelligence/use-crystallized-brain.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 837 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00837
Opus 5	$0.00028	$0.00418
Sonnet 5	$0.00011	$0.00167
Haiku 4.5	$0.00006	$0.00084

Measured 6d ago against content hash 6e1316b3e61f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

use-crystallized-brain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/use-crystallized-brain/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Crystallized Brain

Procedure for agents. The brain holds mastery; this skill holds how to retrieve it cheaply.

When to use

User or project has BRAIN_ROOT pointing at a brain (brain.yaml + corpus/)
MCP server exposes brain_bootstrap, brain_expand, brain_search, brain_get_document
Domain question needs curated knowledge, not a repo-wide file dump

Setup (once per machine)

export BRAIN_ROOT=/path/to/your-brain   # or examples/demo-brain in this repo

MCP: see docs/AGENT-INTEGRATION.md and docs/mcp-config.example.json.

Retrieval protocol (always follow)

Bootstrap first — brain bootstrap <domain> or brain_bootstrap(domain)
- Loads _crystal/seed.md + principles.md (~200–2.5K tokens)
- Enough for orientation and most routine answers
Expand only if needed — brain expand <domain> --query "..." --max-tokens 4000 --max-tier 3
- Tier-ranked: lower source_tier wins (0 = first-party)
- Default max_tier=3 unless user explicitly wants transcripts/social (4–5)
Search for paths — brain search <domain> "keyword" when you need filenames, not full bodies
Get one file — brain get <domain> <relative-path> for a single document
Never read entire sources/ trees or bulk-load corpus/ into context

Conflict resolution

When documents disagree:

Lower quality.source_tier (from frontmatter) wins
Higher quality.verification wins (canonical > expert_verified > …)
Higher quality.confidence wins
Prefer _crystal/ over knowledge/ over sources/ for operational answers

CLI examples

python tools/bin/brain.py domains
python tools/bin/brain.py bootstrap specialty-coffee
python tools/bin/brain.py bootstrap b2b-discovery
python tools/bin/brain.py expand b2b-discovery --query "disqualify" --max-tokens 4000 --max-tier 3
python tools/bin/brain.py search b2b-discovery "qualification"

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 93 lines · 56 tokens per session scan A 6e1316b3e61f

Subscribe to this mod's changes

use-crystallized-brain is a skill published in the GitHub repository bcharleson/crystallized-intelligence (5 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 837 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens