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/jayminwest/kotadb/claude-mdgit clone --depth 1 https://github.com/jayminwest/kotadbWrote 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/instructions/jayminwest/kotadb/claude-md)<a href="https://agentmods.dev/instructions/jayminwest/kotadb/claude-md"><img src="https://agentmods.dev/badge/instructions/jayminwest/kotadb/claude-md.svg" alt="Measured on agentmods" 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 | $0.01180 | $0.01180 |
| Opus 5 | $0.00590 | $0.00590 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
kotadb 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 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
BLUF
KotaDB is a local-only code intelligence API (Bun + TypeScript + SQLite). Use /do for everything.
Quick Start
Primary Entry Point:
/do <request>
The /do command routes your request to the appropriate workflow:
- GitHub issues:
#123, URLs, or SDLC keywords - Expert domains: Claude config and agent authoring tasks
- Questions: "How do I..." style queries
Examples:
/do #123 # Work on GitHub issue
/do "Create a slash command for X" # Claude config task
/do "What tools should an agent have?" # Question
Preserved Commands
For specific operations, these commands remain available:
| Category | Commands |
|---|---|
| Git | /git:commit, /git:pull_request |
| Issues | /issues:feature, /issues:bug, /issues:chore, /issues:refactor, /issues:classify_issue, /issues:audit, /issues:prioritize |
| Tools | /tools:install, /tools:tools |
| Docs | /docs:load-ai-docs |
| Release | /release:release |
Expert Domains
Ten expert domains provide specialized knowledge with plan, build, improve, and question agents:
| Domain | Purpose | Location |
|---|---|---|
claude-config |
.claude/ configuration (commands, hooks, settings) | .claude/agents/experts/claude-config/ |
agent-authoring |
Agent creation (frontmatter, tools, registry) | .claude/agents/experts/agent-authoring/ |
database |
SQLite schema, FTS5, migrations, queries | .claude/agents/experts/database/ |
api |
HTTP endpoints, MCP tools, Express patterns | .claude/agents/experts/api/ |
testing |
Antimocking, Bun tests, SQLite test patterns | .claude/agents/experts/testing/ |
indexer |
AST parsing, symbol extraction, code analysis | .claude/agents/experts/indexer/ |
github |
Issues, PRs, branches, GitHub CLI workflows | .claude/agents/experts/github/ |
automation |
ADW workflows, agent orchestration, worktree isolation | .claude/agents/experts/automation/ |
documentation |
Documentation management, content organization | .claude/agents/experts/documentation/ |
web |
Web content, design system, marketing site | .claude/agents/experts/web/ |
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 · 115 lines · 1,180 tokens per session scan A 682a4ec7f209
kotadb CLAUDE.md is an instructions file published in the GitHub repository jayminwest/kotadb (102 stars, last pushed 4mo ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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 2026-08-30.
Other instructions, from other repositories
lamina typescript.instructions.md
Guidelines for using modern TypeScript features (v5.0-v5.8).
promptscript typescript.instructions.md
Instructions for mrwogu/promptscript, a project described as: Prompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding assistant.
hash rust-review.instructions.md
Review guidance for Rust changes.
hash typescript-review.instructions.md
Review guidance for TypeScript/JavaScript changes.
orm CLAUDE.md
Claude Code instructions for prisma/orm, a project described as: Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB.
anilist-mcp-server AGENTS.md
AGENTS.md instructions for Grinv/anilist-mcp-server, covering agents.md, project shape, why this server exists, commands and conventions.