Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jordiboehme/crystalline --skill crystalline-schemagit clone --depth 1 https://github.com/jordiboehme/crystallineWrote 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.
[](https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-schema)<a href="https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-schema"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-schema/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-schema"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.01785 |
| Opus 5.5 | $0.00021 | $0.00714 |
| Sonnet 5.5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
crystalline-schema 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crystalline Schema
A domain's engrams need no schema by default - type and status are free-form strings. Reach for a schema engram once a domain wants a given type to carry a consistent shape: required observation categories, required relations, or expected frontmatter fields.
Authoring a schema engram
A schema is itself an engram, type: schema, whose frontmatter declares the shape for another type via entity. Body content is optional prose describing the schema; the shape lives entirely in frontmatter.
Before deciding which categories and relations to require, call vocabulary for the domain to see what its engrams already use - it complements infer_schema by grounding the shape in real terms.
---
type: schema
title: Decision Schema
tags:
- schema
- engineering
status: stable
entity: decision
version: 1
schema:
summary: string, one line summary of the decision
rationale?: string
priority(enum):
- low
- medium
- high
alternative?(array): string
supersedes?: Decision
settings:
validation: warn
frontmatter:
status(enum):
- stable
- proposed
- superseded
owner: string
---
# Decision Schema
Engrams of type `decision` in the engineering domain follow this shape.
That is the on-disk shape. Through the MCP write tool none of that frontmatter goes into content - write_engram builds the frontmatter itself from its arguments, and entity, version, schema and settings travel through metadata as an object:
{
"tool": "write_engram",
"arguments": {
"domain": "engineering",
"title": "Decision Schema",
"type": "schema",
"tags": ["schema", "engineering"],
"metadata": {
"entity": "decision",
"version": 1,
"schema": {
"summary": "string, one line summary of the decision",
"priority(enum)": ["low", "medium", "high"]
},
"settings": { "validation": "warn" }
},
"content": "The shape for decision engrams.\n\n- [convention] Decisions carry a summary and a priority #schema\n- [convention] Adopted in warn mode first #schema"
}
}
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.
- 1mo ago First seen · 131 lines · 52 tokens per session scan A 0f3abd72dbe1
crystalline-schema is a skill published in the GitHub repository jordiboehme/crystalline (17 stars, last pushed 2d ago), licensed MPL-2.0. It adds 52 tokens to every session and 1,785 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract…
binder-modeling
Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.
binder-import
Import external data into a Binder workspace. Handles CSV, JSON, YAML, Markdown files, and directories of Markdown. Use when asked to "import data", "load records from a file", "ingest documents", "migrate data into binder", or bulk-create records from an external source.
binder-cli
Binder CLI for knowledge graph operations — CRUD, search, schema inspection, transaction import, docs rendering. Use when asked to "query binder", "search records", "create a record", "check the schema", "import transactions", "undo changes", or work with a binder workspace.
mdvs
Use mdvs search for any content lookup in a markdown directory — semantic / hybrid / SQL-filtered, beats Grep / Glob for finding by meaning. mdvs init infers a schema from existing markdown, mdvs check validates frontmatter, mdvs update evolves the schema as the KB grows. Activate whenever the project contains…
mfs-find
Search, grep, browse, and read across registered MFS data sources via the mfs CLI — codebases, docs, PDFs, web crawls, databases (postgres/mysql/mongo/snowflake/bigquery), issue trackers (jira/linear/github), CRMs (hubspot), chat (slack/discord/gmail/feishu), object stores (s3/gdrive). Use whenever the user asks to…