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/n0an/vivagents/claude-mdgit clone --depth 1 https://github.com/n0an/vivagentsWrote 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/n0an/vivagents/claude-md)<a href="https://agentmods.dev/instructions/n0an/vivagents/claude-md"><img src="https://agentmods.dev/badge/instructions/n0an/vivagents/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 | $0.00478 | $0.00478 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
vivagents CLAUDE.md scanned grade A with 1 finding 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **CLI spawning:** `node:child_process.spawn` with timeout What it actually says
CLAUDE.md
Project Overview
VivAgents is a standalone HTTP server that wraps CLI AI tools (Claude Code, Codex CLI, Gemini CLI) behind a simple REST API. It's extracted from VivaDicta macOS app's embedded CLI server to run independently on any machine — Mac, Linux VPS, or Docker.
Primary use case: VivaDicta iOS/macOS apps connect to VivAgents over the network for AI text processing, instead of requiring a Mac running VivaDicta.
Build & Run
npm install
npm run build # tsc → dist/
npm start # node dist/index.js (starts server)
node dist/index.js check # Check which CLIs are available
node dist/index.js token # Show auth token
Architecture
- Runtime: Node.js + TypeScript (ESM)
- HTTP: Raw
node:http(no Express — only 3 routes) - CLI spawning:
node:child_process.spawnwith timeout - Config:
~/.vivagents/config.json+ env vars + CLI args (cascading priority) - Auth: Bearer token stored in
~/.vivagents/token
Key files
src/index.ts— Entry point, CLI arg parsing, commandssrc/server.ts— HTTP server, routing, authsrc/config.ts— Config loading cascadesrc/providers/— Claude, Codex, Gemini CLI providerssrc/providers/discovery.ts— Binary discovery (PATH, nvm, known locations)src/routes/—/health,/models,/enhancehandlerssrc/utils/— Process spawning, error detection
API
GET /health— Server status + provider availabilityGET /models— Available models per providerPOST /enhance— Process text through a CLI provider
All endpoints require Authorization: Bearer <token> header.
Conventions
- Copyright © 2026 Anton Novoselov
- API is 100% backward-compatible with VivaDicta macOS
ClaudeCLIServerand iOSClaudeCLIServerClient - No external dependencies beyond TypeScript + @types/node
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.
- 5d ago First seen · 47 lines · 478 tokens per session scan A b424a3f6dd54
vivagents CLAUDE.md is an instructions file published in the GitHub repository n0an/vivagents (5 stars, last pushed 4mo ago), licensed MIT. It adds 478 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
flt CLAUDE.md
Instructions for twaldin/flt, covering flt, the soul of the project: primitives, not a monolith, architecture, repo map and conventions.
flt AGENTS.md
Instructions for twaldin/flt, a project described as: cli-first harness agnostic agent orchestration tool.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
parallel-code CLAUDE.md
Claude Code instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
ox AGENTS.md
AGENTS.md instructions for sageox/ox, covering human attention is the scarcest resource, what is ox?, quick start, terminology and required reviews.