Borrowing it
Nothing to install: this file belongs to VoidNxSEC/securellm-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/VoidNxSEC/securellm-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/VoidNxSEC/securellm-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/voidnxsec/securellm-mcp/claude-md)<a href="https://agentmods.dev/instructions/voidnxsec/securellm-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/voidnxsec/securellm-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/voidnxsec/securellm-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/voidnxsec/securellm-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 | $0.00436 | $0.00436 |
| Opus 5.5 | $0.00174 | $0.00174 |
| Sonnet 5.5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
securellm-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 23d 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.
What it actually says
securellm-mcp
MCP server for the SecureLLM suite. Built with TypeScript/Node.js.
Machine: Ubuntu (/home/nx)
This server runs on Ubuntu with user nx. All paths use /home/nx/.
Build
npm run build
TypeScript is a per-project dependency (node_modules/.bin/tsc), not global. Always rebuild after source changes before restarting the server.
MCP Configuration
The server is configured globally so it connects from any project directory:
- Global config:
~/.claude/claude.json - Per-project config (this repo):
.mcp.json— kept in sync with the global config
The .mcp.json exists for local dev convenience but the global config is the canonical one. If you update env vars or paths, update both files.
Key environment variables
| Variable | Value | Purpose |
|---|---|---|
ADR_REPO_PATH |
/home/nx/suit/adr-ledger |
Where ADR tools look for the ledger |
PROJECT_ROOT |
/home/nx/suit |
Suite root |
KNOWLEDGE_DB_PATH |
/home/nx/.local/share/securellm/knowledge.db |
SQLite knowledge base |
Why ADR_REPO_PATH matters
adr_new and adr_show write/read files directly using ADR_REPO_PATH. adr_list, adr_accept, etc. delegate to bash /home/nx/suit/adr-ledger/scripts/adr — the script auto-detects its location via ADR_ROOT, but the env var makes it explicit.
Previous machine (kernelcore)
The original .mcp.json had paths pointing to /home/kernelcore/ (different machine). When migrating to a new machine, update all absolute paths in both ~/.claude/claude.json and .mcp.json.
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.
- 23d ago First seen · 41 lines · 436 tokens per session scan A d352fcb590fb
securellm-mcp CLAUDE.md is an instructions file published in the GitHub repository VoidNxSEC/securellm-mcp (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 436 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-10-05.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.