Borrowing it
Nothing to install: this file belongs to SmartDogg/mnela. 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/SmartDogg/mnela/main/CLAUDE.mdgit clone --depth 1 https://github.com/SmartDogg/mnelaWrote 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/smartdogg/mnela/claude-md)<a href="https://agentmods.dev/instructions/smartdogg/mnela/claude-md"><img src="https://agentmods.dev/badge/instructions/smartdogg/mnela/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/smartdogg/mnela/claude-md"><img src="https://agentmods.dev/badge/instructions/smartdogg/mnela/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 | $0.03014 | $0.03014 |
| Opus 5.5 | $0.01206 | $0.01206 |
| Sonnet 5.5 | $0.00603 | $0.00603 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade D, and why
mnela CLAUDE.md scanned grade D with 3 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `scripts/install.sh` — one-command VPS bootstrap (`curl … | sudo bash`). Generates `.env` with random secrets, clones to `/opt/mnela`, materialises a Caddyfile, runs the `migrate` one-shot compose service, issues the i Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `scripts/install.sh` — one-command VPS bootstrap (`curl … | sudo bash`). Generates `.env` with random secrets, clones to `/opt/mnela`, materialises a Caddyfile, runs the `migrate` one-shot compose service, issues the i Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `scripts/install.sh` — one-command VPS bootstrap (`curl … | sudo bash`). Generates `.env` with random secrets, clones to `/opt/mnela`, materialises a Caddyfile, runs the `migrate` one-shot compose service, issues the i How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnela — developer guide for Claude Code
This file is read by Claude Code when working inside the Mnela repo. The Server-Brain instruction template that the runtime Claude subprocess uses lives at infra/claude/CLAUDE.md.template — DO NOT confuse the two.
Architecture overview
apps/api— NestJS HTTP API./search/askSSE stream,/admin/*panels,/system/configtyped registry,/admin/providersLLM CRUD,/projects(incl. suggestions + preview + dismiss).apps/orchestrator— NestJS process running BullMQ consumers: enrichment, project-context, vision (analyze_attachment), claude-status boot, and the newprojectsconsumer (project_suggest debounced post-enrichment + project_autofill). See ADR-0051.apps/worker— ingestion worker (parsers, attachment promotion).apps/mcp— HTTP MCP transport for external tools.apps/tg-bot— Telegram bot frontend over/search/ask+/documents/upload. Single-tenant: oneTelegramBotsingleton row +TelegramAllowedUserwhitelist. Configured under/admin/system → Telegram; hot-reloaded viamnela:eventstelegram:reloadchannel. grammY + Bot API 9.5sendMessageDraftstreaming. Multi-modal turn bundling (debouncetelegram.bundleWindowMs) merges voice + photo + text into one /ask call. See ADR-0053.apps/web— Next.js 15 UI. v1 menu has three sections: Workspace (/,/graph,/ask), Library (/documents,/projects,/inboxshown as "Review"), Admin (/activity,/admin/system)./projects(Active/Suggested/Dismissed tabs),/projects/new(suggestion grid + manual create + autofill),/projects/[slug](Files/Timeline/Entities/Decisions/Questions + Ask-scope deep-link) — the Decisions tab owns the per-project list and Create flow (no standalone/decisionspage)./activityis the single home for?tab=uploads(was/imports) and?tab=queue(was/jobs); legacy URLs redirect there./admin/systemis the only admin route — it folds in AI Providers + Claude Code status (expand) + Storage stats + API tokens (was/admin/tokens). See ADR-0052.packages/llm-providers— the only place AI calls flow through. See ADR-0049.packages/mcp-tools—@mnela/mcp-toolsregistry.invokeTool(name, input, ctx)is the shared entry point for both the MCP host and the in-process agent loop.packages/core—system-registry.ts: typedSystemConfigkeys +readRegistryValueshared by api/orchestrator/worker.packages/db— Prisma schema + repositories. Migrations are hand-written whenmigrate devis impractical on Windows (see ADR-0048 stopgap pattern).packages/claude-runner— low-level wrapper around theclaudeCLI subprocess. Never import directly from app code — go through@mnela/llm-providers.
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.
- 2mo ago First seen · 85 lines · 3,014 tokens per session scan D 4f73d49b0c67
mnela CLAUDE.md is an instructions file published in the GitHub repository SmartDogg/mnela (1 stars, last pushed 3mo ago), licensed MIT. It adds 3,014 tokens to every session, about $0.0121 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.