Borrowing it
Nothing to install: this file belongs to omercagatay/bddk-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/omercagatay/bddk-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/omercagatay/bddk-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/omercagatay/bddk-mcp/claude-md)<a href="https://agentmods.dev/instructions/omercagatay/bddk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/omercagatay/bddk-mcp/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.
<a href="https://agentmods.dev/instructions/omercagatay/bddk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/omercagatay/bddk-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01842 | $0.01842 |
| Opus 5 | $0.00921 | $0.00921 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
bddk-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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDDK MCP Server
MCP server for Turkish banking regulatory intelligence (BDDK) — search decisions, regulations, bulletins, and statistical data. PostgreSQL + pgvector backend, offline-first embeddings, airlocked serving: retrieval tools answer only from the locally published corpus release; live BDDK/mevzuat access is confined to the bulletin, announcement, and institution-directory tools (plus the live announcement/bulletin half of get_regulatory_digest) and ingest/operator paths. All live access is confined to the exact-host HTTPS allowlist (bddk.org.tr / mevzuat.gov.tr only), enforced by core/outbound_http.py and, for document streaming, the equivalent bounded path in ingest/doc_sync.py.
Commands
# docker compose parses the operator service's required variables even for
# db-only startup; export placeholders once per shell (never real IdP values):
export BDDK_JWT_JWKS_URL=https://placeholder.invalid/jwks BDDK_JWT_ISSUER=https://placeholder.invalid
docker compose up -d bddk-test-db # PostgreSQL + pgvector + the bddk_test pytest fixture
docker compose up -d db # DB only (postgres-marked tests then skip; prefer bddk-test-db)
uv sync --dev # Install runtime + dev dependencies
uv sync --group gpu # Add CUDA torch + chandra-ocr (for doc_sync OCR path)
uv run python server.py # Run MCP server (root shim; needs db up + BDDK_DATABASE_URL)
uv run bddk-mcp serve # Same, via the packaged CLI (also: migrate, bootstrap, admin-ui)
uv run bddk-mcp migrate # Create/upgrade the PostgreSQL schema (versioned migrations)
uv run python seed.py import # Seed DB from seed_data/ (shim for bddk-seed)
uv run python seed.py export # Export DB to seed_data/
uv run pytest tests/ -m "not postgres and not gpu" -v # DB-less unit run (matches CI unit job)
BDDK_REQUIRE_TEST_DATABASE=1 uv run pytest tests/ -m "postgres and not gpu" -v # DB-backed run (matches CI; fails loudly, never skips, if the DB is absent)
uv run pytest tests/test_client.py -v # Run single test file
uv run ruff check . # Lint
uv run ruff format . # Format
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.
- 4d ago Changed · +4 lines · +185 tokens per session bf3ca45d40ab
- 9d ago First seen · 62 lines · 1,657 tokens per session scan A c8a078422f88
bddk-mcp CLAUDE.md is an instructions file published in the GitHub repository omercagatay/bddk-mcp (11 stars, last pushed 2d ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 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
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.