What is obsidian-hybrid-search CLAUDE.md?

A set of Claude Code instructions for the obsidian-hybrid-search project. It describes the project’s checks and the steps agents should follow before committing code.

Use it when modifying the obsidian-hybrid-search codebase, especially its search logic. It provides commands for building, testing, checking code quality, and running relevant integration tests.

It helps coding agents verify changes consistently instead of relying only on a successful build. The checks include tests, linting, formatting, unused-code checks, and extra search-related verification when needed.

How flowing-abyss/obsidian-hybrid-search configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to flowing-abyss/obsidian-hybrid-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/flowing-abyss/obsidian-hybrid-search/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/flowing-abyss/obsidian-hybrid-search

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/flowing-abyss/obsidian-hybrid-search/claude-md/github.svg)](https://agentmods.dev/instructions/flowing-abyss/obsidian-hybrid-search/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/flowing-abyss/obsidian-hybrid-search/claude-md"><img src="https://agentmods.dev/badge/instructions/flowing-abyss/obsidian-hybrid-search/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/flowing-abyss/obsidian-hybrid-search/claude-md"><img src="https://agentmods.dev/badge/instructions/flowing-abyss/obsidian-hybrid-search/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,902 This file is loaded in full into every session.

When invoked 1,902 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01902	$0.01902
Opus 5	$0.00951	$0.00951
Sonnet 5	$0.00380	$0.00380
Haiku 4.5	$0.00190	$0.00190

Measured 11d ago against content hash 8959b64fe7ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

obsidian-hybrid-search 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 11d 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.

CLAUDE.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Guide for AI Agents

Quick Reference

npm run build          # TypeScript compile (must pass before committing)
npm test               # Unit tests with no external services
npm run test:integration  # Integration tests with configured or local embeddings
npm run test:e2e-watcher  # Real file-watcher integration test
npm run coverage       # Unit coverage with thresholds from vitest.config.ts
npm run knip           # Dead code / unused exports check (0 issues required)
npm run lint           # ESLint (0 errors required; warnings on `any` are ok)
npm run format         # Prettier write (run before committing)
npm run format:check   # Prettier check (used in CI)

Pre-commit hooks run lint-staged. The pre-push hook runs npm run preflight and adds the ranking quality gate when relevant search code changed.

Agent Verification Checklist

Run this sequence after any code change to get full feedback before committing:

npm run format && npm run build && npm test && npm run lint && npm run knip

After modifying searcher.ts:

Run npm test for graph traversal, filters, cache behavior, and result contracts
Run eval before and after changes that can affect ranking quality

After modifying db.ts:

npm test catches NFD path storage, model change wipe, link integrity (test/db.test.ts)
If you changed the DB schema (new columns, new tables, altered FTS structure), delete the eval fixture DB and regenerate both committed baselines with the local model.
```
rm -f fixtures/obsidian-help/dataset/.obsidian-hybrid-search.db
npm run eval -- --output eval/results/baseline-no-rerank.json
npm run eval -- --rerank --output eval/results/baseline-rerank.json
```
Do not lower the floors in eval/quality.ts to match a regression.

After modifying the MCP schema in mcp-runtime.ts:

npm run build verifies that MCP parameter names map to valid SearchOptions fields
If you add a search parameter, update SearchOptions in searcher.ts, the schema in mcp-runtime.ts, and CLI flags in cli.ts
npm test catches result shape changes (test/contract.test.ts)

Read the full file on GitHub · 180 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.

11d ago First seen · 180 lines · 1,902 tokens per session scan A 8959b64fe7ca

Subscribe to this mod's changes

obsidian-hybrid-search CLAUDE.md is an instructions file published in the GitHub repository flowing-abyss/obsidian-hybrid-search (103 stars, last pushed 10d ago), licensed MIT. It adds 1,902 tokens to every session, about $0.0095 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.

mcp obsidian search semantic-search sqlite vector-search

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

obsidian-hybrid-search: Instructions file for Claude Code