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/dorukyelken/model-database-protocol/claude-mdgit clone --depth 1 https://github.com/DorukYelken/Model-Database-ProtocolWhat 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 | $0.01564 | $0.01564 |
| Opus 5 | $0.00782 | $0.00782 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
Model-Database-Protocol 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 73 lines · 1,564 tokens per session scan A deadc0fbedcb
Model-Database-Protocol CLAUDE.md is an instructions file published in the GitHub repository DorukYelken/Model-Database-Protocol (8 stars, last pushed 4mo ago), with no licence file. It adds 1,564 tokens to every session, about $0.0078 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
presidio recognizers.instructions.md
Instructions for data-privacy-stack/presidio, covering recognizer changes, the load-bearing rule: test the configuration path, placement and naming, pattern scores and context words.
presidio copilot-instructions.md
Copilot instructions for data-privacy-stack/presidio, covering presidio development & review instructions, core philosophy, backward compatibility, cross-component changes and security & privacy.
presidio AGENTS.md
AGENTS.md instructions for data-privacy-stack/presidio, covering presidio — agent guidelines, working in this repo, adding a pii recognizer, changing the yaml configuration layer and general engineering rules.
sqlglot AGENTS.md
Instructions for tobymao/sqlglot, covering contributing to sqlglot, about sqlglot, development commands, installation and basic installation.
presidio yaml-config.instructions.md
Instructions for data-privacy-stack/presidio, covering yaml configuration & pydantic validation layer, schema/constructor sync, extra must be a deliberate choice, excludenone discipline on kwargs models and fail early, with actionable messages.
tuva-core AGENTS.md
Instructions for tuva-health/tuva-core, covering tuva core agent operating manual, tuva core 1.0 contract, repository boundaries, architecture and public-contract rules and extension columns.