Borrowing it
Nothing to install: this file belongs to gwdmnn/keyward-mcp-server. 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/gwdmnn/keyward-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/gwdmnn/keyward-mcp-serverWrote 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/gwdmnn/keyward-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/gwdmnn/keyward-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gwdmnn/keyward-mcp-server/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 | $0.01957 | $0.01957 |
| Opus 5 | $0.00979 | $0.00979 |
| Sonnet 5 | $0.00391 | $0.00391 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
keyward-mcp-server 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — db-mcp-server
Guidance for Claude Code when working in this repository.
What this is
A local MCP server (Python, stdio) that gives Claude Code routed, credential-isolated access to customer PostgreSQL databases. Claude sends only SQL and receives only rows; DB usernames/passwords and SSH PEM keys never enter the model's context. It replaces the old database-connection skill (which read .env files and embedded passwords into psql commands — leaking them into the transcript).
Design docs (read these before changing behavior). Available in English (docs/en/) and Portuguese (docs/pt/); the Portuguese versions are the originals:
- docs/en/FDD-db-mcp-server.md — Feature Design Document (authoritative; contracts in §5). PT: docs/pt/FDD-db-mcp-server.md.
- docs/en/IMPLEMENTATION-PLAN-fase1.md — milestones M0–M9, module signatures, test strategy. PT: docs/pt/IMPLEMENTATION-PLAN-fase1.md.
- Diagrams: docs/en/c4/ (PlantUML C4) and docs/en/mermaid/ (Mermaid); PT under docs/pt/.
Core security invariants — do not violate
- No secret ever reaches the model's context. No MCP tool may accept or return a DB username/password, full DSN, or PEM contents. Credential writes are out-of-band via the
db-vaultCLI only — never an MCP tool. - The server's stdout is the MCP protocol channel. NEVER
print()(or otherwise write to stdout) from any code path the server reaches — it corrupts the stdio protocol. Use stderr/logging if needed.print()is fine only in the operator CLIs (vault_admin,bootstrap), which run in a terminal. - Passphrase from the environment (
DB_MCP_PASSPHRASE) — via the shell, a.envfile (loaded byconfig.py; real env wins), or agetpassprompt — never from argv, the catalog, or a log. DB passwords indb-vaultare read viagetpass, never argv. Caveat: puttingDB_MCP_PASSPHRASEin.envstores the vault passphrase in plaintext on disk next tovault.enc; prefer keeping only the path vars in.envand supplying the passphrase via shell/prompt. - Never print secret values from
bootstrap/db-vault— only counts and non-secretsecret_refs (customer/env/service). - Fresh AES-GCM nonce on every seal; atomic vault writes (temp +
os.replace). Both already enforced incrypto.py— keep it that way. vault.enc,keys/,*.env,*.pemare git-ignored. Never commit them; never add a secret toregistry.yaml(it is non-secret routing only).
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.
- 7d ago First seen · 79 lines · 1,957 tokens per session scan A a28f97aff291
keyward-mcp-server CLAUDE.md is an instructions file published in the GitHub repository gwdmnn/keyward-mcp-server (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 1,957 tokens to every session, about $0.0098 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.