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 agentmods add instructions/shinyobjectz/montology/claude-mdgit clone --depth 1 https://github.com/shinyobjectz/montologyWhat 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 | $0.00444 | $0.00444 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
montology CLAUDE.md 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 yesterday.
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.
What it actually says
montology — repo instructions
Public repo, shinyobjectz/montology. Also mounted as a submodule of the
private socialite repo — never assume socialite's code or vocabulary is
reachable from here; this repo stands alone.
What this is: the ontology context layer for any monorepo — a
vocabulary as a database, enforced against the code by a tree-sitter scan.
Nothing else. The marketing era ended at the marketing-era tag; do not
resurrect it here.
The shape
.monty/core— workspace discovery (walk up for.monty, like git)..monty/onto— the database: word / doctrine / overload / gen_runs. Montology's own words are authored ONLY inseed.py(just seed)..monty/scan— the multiast layer: tree-sitter declarations per language, the lint (collision / code-resolution / drift), candidates mining, ast-grep invoked for structural search..monty/gen—sync(deterministic render of the words skill),gen_word(atomic-tier drafts under law),lint(the drift gate + the no-prompt ban)..monty/cli—monty;.plugin/— the Agent Plugins face;npm/— the launcher.
Ground rules
- Dogfood: this repo is itself a montology workspace.
monty onto check <name>before naming anything;just checkrunsmonty lint, so a collision or a stale words skill fails the build here too. - Prose is rendered, never authored.
.claude/skills/words/SKILL.mdis GENERATED (monty sync); hand edits are lost and lint catches them. - Errors are data with the repair attached. A word means one thing. Vendors are not vocabulary.
- This repo is public: nothing tenant-specific, nothing credentialed, nothing from socialite's private tree crosses into it.
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.
- yesterday First seen · 37 lines · 444 tokens per session scan A a552d6c4fd87
montology CLAUDE.md is an instructions file published in the GitHub repository shinyobjectz/montology (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 444 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
oh-my-design CLAUDE.md
Instructions for kwakseongjae/oh-my-design, a project described as: Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.
Sigil-UI AGENTS.md
Instructions for Kevin-Liu-01/Sigil-UI, covering sigil ui — agent instructions, the #1 rule, how it works, quick reference: what to edit for common tasks and repository structure.
design-md-extractor CLAUDE.md
Instructions for jpoindexter/design-md-extractor, covering claude.md, commands, run a single test file, cli usage (after build) and architecture.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.
design-pipeline CLAUDE.md
Instructions for 2233admin/design-pipeline, a project described as: 给 AI Agent 的前端设计管线：先写 DESIGN.md 与 MOTION.md，经 job 分发、OpenSpec 与证据门禁再写代码。.
Standby.Design CLAUDE.md
Claude Code instructions for KarstenKreh/Standby.Design, covering claude.md, npm publish (standby-design-mcp), deploys (website + remote mcp server) and pitfalls.