agentmods.dev

schema-unify

schema-unify is a skill for Claude Code, Codex from timurgaleev/memex. It costs 85 tokens per session (2,607 once invoked), scanned A, original, MIT.

A migration workflow for replacing many inconsistent page-type labels with a shared set of 15 canonical types and related subtypes. It also handles aliases and links created during the migration.

In plain words
What is it for?
It helps check for type proliferation, run a durable type-unification job, and clean up dangling aliases.
Why use it?
It removes type clutter that builds up in a long-lived knowledge base, making its structure easier to maintain and query.

Skill for Claude CodeCodex

not rated 8 3d ago A scan 85 tokens original MIT
View the source file timurgaleev/memex
Install

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.

agentmods
npx agentmods add skills/timurgaleev/memex/schema-unify
Any agent
npx skills add timurgaleev/memex --skill schema-unify
Clone the repo
git clone --depth 1 https://github.com/timurgaleev/memex

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.

agentmods badge for schema-unify

README.md
[![agentmods](https://agentmods.dev/badge/skills/timurgaleev/memex/schema-unify.svg)](https://agentmods.dev/skills/timurgaleev/memex/schema-unify)
Your own site
<a href="https://agentmods.dev/skills/timurgaleev/memex/schema-unify"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/schema-unify.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,607 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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.02607
Opus 5 $0.00043 $0.01303
Sonnet 5 $0.00017 $0.00521
Haiku 4.5 $0.00009 $0.00261

Measured 5d ago against content hash f80e75e05cbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

schema-unify 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 5d 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.

deploy/skills/schema-unify/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schema Unification (noisy types → canonical taxonomy)

The brain ships a 15-type DRY/MECE canonical taxonomy (14 canonical + note catch-all), recorded on the concepts/type-conventions page. Brains that accreted noisy per-source types over years of ingestion opt in via the doctor's type-proliferation finding + a durable unify-types job that is PROTECTED (never auto-fired by the background cycle).

This skill is the playbook for that migration.

brain_first: exempt

This skill is ABOUT the brain's shape — it can't depend on the brain it's reshaping. No search lookup first; jump straight to the doctor.

When this skill fires

  • Agent runs run_doctor (or memex doctor on the host) and sees a type-proliferation or dangling-alias warning
  • User asks "what is the canonical taxonomy / how do I clean up my page types / migrate to canonical"
  • A dangling-aliases finding surfaces (post-unify GC)
  • An agent ingesting from a custom source wants to consult the canonical taxonomy as a reference

Mental model (one paragraph)

A long-lived brain accretes dozens of distinct frontmatter type values over years of ingestion: tweet / tweet-thread / tweet-bundle / tweet-single / media/x-tweet/bundle / tweet-stub all coexisting; thousands of concept-redirect pages; partner-link pages that should be links; civic / framework / insight / memo / anecdote one-offs. The cure: collapse to 15 canonical types (person, company, media, tweet, social-digest, analysis, atom, concept, source, deal, email, slack, writing, project, note) with subtype/format/origin pushed to frontmatter, slug-alias rows for redirects, real link rows for edge-shaped pages, and a catch-all that bins long-tail unknowns to note with frontmatter.legacy_type = <original> for rollback.

Workflow

Phase 1: Discovery

Confirm the brain actually has proliferation (not already canonical).

ontology_get

If the observed type set is already ≤16 distinct values matching the canonical list on concepts/type-conventions, the brain is already unified — skip the migration.

Read the full file on GitHub · 301 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.

  1. 5d ago First seen · 301 lines · 85 tokens per session scan A f80e75e05cbc

Subscribe to this mod's changes

schema-unify is a skill published in the GitHub repository timurgaleev/memex (8 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 2,607 once invoked, about $0.0004 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.

Backend and APIsDatabasesbunclaudeknowledge-basemcpmodel-context-protocolpgvector
Related

Other skills, from other repositories

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/obsidian-mcp-server · 85 tokens

api-mirror

Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.

cyanheads/obsidian-mcp-server · 68 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/wikidata-mcp-server · 85 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/nonprofit-explorer-mcp-server · 85 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/wikipedia-mcp-server · 85 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/openstates-mcp-server · 85 tokens