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/theepicsaxguy/qdrant-codebase-mcp/claude-mdgit clone --depth 1 https://github.com/theepicsaxguy/qdrant-codebase-mcpWrote 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/theepicsaxguy/qdrant-codebase-mcp/claude-md)<a href="https://agentmods.dev/instructions/theepicsaxguy/qdrant-codebase-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/theepicsaxguy/qdrant-codebase-mcp/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 | $0.01603 | $0.01603 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
qdrant-codebase-mcp 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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — qdrant-codebase-mcp
This file gives Claude Code the context it needs to work effectively in this repository.
What this project is
An MCP (Model Context Protocol) server that indexes a codebase into Qdrant (a vector database) using FastEmbed embeddings, then exposes semantic search tools to AI assistants. Users run it via npx qdrant-codebase-mcp and their AI assistant can call search_code("JWT validation logic") to find relevant code by meaning.
Commands
npm run dev # run with tsx watch (rebuilds on save)
npm run typecheck # tsc --noEmit — must pass before committing
npm run lint # ESLint strict — zero warnings tolerated
npm test # vitest unit tests (tests/unit/)
npm run build # compile src/ → dist/
npm run knip # find dead exports / unused deps
npm run audit # npm audit --audit-level=moderate
npm run changeset # describe a change before opening a PR
DRY_RUN=1 ./scripts/publish.sh # validate publish without publishing
./scripts/publish.sh --dry-run # same
./scripts/publish.sh --ci # non-interactive CI mode
Architecture
src/
mcp-entry.ts entry point for MCP stdio transport
index.ts entry point for HTTP service
bootstrap.ts wires all services together; call startIndexing() to activate
config/
schema.ts Zod schema — all config with defaults lives here
loader.ts loads from env vars or config.yml; env takes precedence
mcp/
server.ts registers MCP tools: search_code, list_repos, get_repo_status, trigger_reindex
indexing/
coordinator.ts fullIndex() and indexFile() — the core indexing loop
watcher/
watcher.ts chokidar file watcher with per-file debounce timers
embedding/
adapter.ts FastEmbed wrapper; lazy-loads model; batch + single embed
qdrant/
adapter.ts Qdrant REST client wrapper; collection lifecycle + upsert/search/delete
search/
service.ts embeds query → searches one or all repos → merges results
scanner/
scanner.ts walks the repo and returns indexable file paths
chunker/
chunker.ts splits files into overlapping line windows
types/
index.ts shared interfaces (IndexedChunk, MetadataPoint, etc.)
logger.ts pino logger factory
metrics.ts prom-client counters and histograms
tests/
unit/ vitest unit tests — no Qdrant/network required
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.
- 3d ago First seen · 132 lines · 1,603 tokens per session scan A bd00d9ba534a
qdrant-codebase-mcp CLAUDE.md is an instructions file published in the GitHub repository theepicsaxguy/qdrant-codebase-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 1,603 tokens to every session, about $0.0080 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
mcp-documentation-server copilot-instructions.md
Instructions for andrea9293/mcp-documentation-server, covering mcp documentation server - ai coding agent instructions, architecture overview, core components, server entry point (src/server.ts) and embedding providers (src/embedding-provider.ts).
pgContext AGENTS.md
Instructions for Evokoa/pgContext, covering agents.md — installing & using pgcontext with an ai agent, what pgcontext is (and why it's worth using), environment facts (pins — do not guess), path a — docker (preferred; zero build, most deterministic) and path b — build from source (when docker is unavailable).
flock copilot-instructions.md
Instructions for dais-polymtl/flock, covering copilot instructions for flock, repository layout, building, setup vcpkg (first time or after clean) and release build.
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
second-brain CLAUDE.md
Claude Code instructions for henrydaum/second-brain, covering second brain — architecture notes, ⚡ the kernel (read first), the layout (trees.py), what ships in the app's tree (bundled/) and the kernel boundary (the one rule).
markdown-vdb CLAUDE.md
Instructions for geckse/markdown-vdb, covering markdown vdb, architecture, project structure, core design decisions and key conventions.