agentmods.dev

agentpulse CLAUDE.md

Project instructions for AgentPulse, a dashboard that monitors and manages AI coding-agent sessions across machines. They describe its technologies, data storage, real-time updates, and project structure.

In plain words
What is it for?
Working on AgentPulse features involving its Bun server, React interface, databases, WebSockets, telemetry, and MCP package.
Why use it?
They help a coding agent understand how the application is built and which commands, services, and conventions it must follow.

Instructions file

16 1mo ago C scan 7,048 tokens original MIT
View the source file jstuart0/agentpulse
Install

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.

agentmods
npx agentmods add instructions/jstuart0/agentpulse/claude-md
Clone the repo
git clone --depth 1 https://github.com/jstuart0/agentpulse
Per session 7,048 This file is loaded in full into every session.
When invoked 7,048 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.07048 $0.07048
Opus 5 $0.03524 $0.03524
Sonnet 5 $0.01410 $0.01410
Haiku 4.5 $0.00705 $0.00705

Measured yesterday against content hash 5131e29fd5ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agentpulse CLAUDE.md scanned grade C with 2 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 yesterday.

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.

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.

- **Relay:** `curl -sSL https://your-server.example.com/setup-relay.sh | bash -s -- --key ap_xxx`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Relay:** `curl -sSL https://your-server.example.com/setup-relay.sh | bash -s -- --key ap_xxx`
CLAUDE.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - AgentPulse

Project Overview

AgentPulse is the command center for AI coding agents across all your machines. It monitors, orchestrates, and manages Claude Code and Codex CLI sessions from a single dashboard with chat-style prompt history, session notes, templates, managed launches, and remote access from any device.

Tech Stack

  • Runtime: Bun
  • Backend: Hono (HTTP framework)
  • Frontend: React 19 + Vite + TailwindCSS
  • State: Zustand
  • Database: SQLite (default, OSS quickstart) and PostgreSQL (production / multi-replica) — set DATABASE_URL=postgres://... to opt into Postgres. SQLite remains default when DATABASE_URL is unset or empty.
  • ORM: Drizzle
  • Real-time: WebSocket (native Bun) + 3s polling fallback
  • Telemetry: Cloudflare Worker + D1 at telemetry-agentpulse.xmojo.net (default homelab endpoint; configurable via TELEMETRY_ENDPOINT env var in src/server/services/telemetry.ts)
  • MCP: @modelcontextprotocol/sdk (stdio transport) + zod (tool input schemas) — lives in the packages/agentpulse-mcp/ workspace member (standalone-publishable as the agentpulse-mcp npm package), see docs/MCP.md and packages/agentpulse-mcp/README.md
  • Linting: Biome

Commands

bun install              # Install dependencies
bun run dev              # Start dev server (API + Vite)
bun run dev:server       # Start API server only
bun run dev:web          # Start Vite frontend only
bun run dev:supervisor   # Start local supervisor only (watch mode)
bun run build            # Production build
bun run start            # Start production server
bun run check            # Run Biome linter
bun run check:fix        # Run Biome linter with auto-fix
bun run check:architecture  # Run all architecture guard scripts
bun run typecheck        # TypeScript type checking
bun run test             # Run test suite (bun test)
bun run test:watch       # Run tests in watch mode
bun run build:mcp        # Build the agentpulse-mcp package to dist/ (tsc, node-portable)
bun run check:mcp-tarball  # Pack agentpulse-mcp for real and audit the tarball (path allowlist, no sourcemaps/lifecycle-scripts/secrets)
agentpulse mcp serve     # Run the MCP server over stdio, from this checkout (for Claude Code / Codex CLI)
agentpulse mcp install   # Mint/reuse a scoped API key, print client config (see docs/MCP.md)

Read the full file on GitHub · 259 lines

Changes

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.

  1. yesterday First seen · 259 lines · 7,048 tokens per session scan C 5131e29fd5ec

Subscribe to this mod's changes

agentpulse CLAUDE.md is an instructions file published in the GitHub repository jstuart0/agentpulse (16 stars, last pushed 1mo ago), licensed MIT. It adds 7,048 tokens to every session, about $0.0352 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsData and AIFrontendai-agentsai-toolingbunclaude-codecodex-clihomelab
Related

Other instructions, from other repositories

codex-studio AGENTS.md

Instructions for gvastethecreator/codex-studio, covering codex studio agent guide, current direction, setup / first run, required context pass and commands.

gvastethecreator/codex-studio · 1,173 tokens

remote-dev-containers AGENTS.md

Instructions for eXPerience83/remote-dev-containers, covering agents.md, sources of truth, mandatory pr discipline, security invariants and runtime implementation rules.

eXPerience83/remote-dev-containers · 1,864 tokens

loop AGENTS.md

Instructions for axeldelafosse/loop, covering quick commands, repo workflows, coding standards, cli-specific notes and testing.

axeldelafosse/loop · 665 tokens

deepwiki-by-cc CLAUDE.md

Instructions for andyhtran/deepwiki-by-cc, covering commands, type checking and testing.

andyhtran/deepwiki-by-cc · 198 tokens

session-map AGENTS.md

Instructions for hao-cyber/session-map, covering sessionmap 项目指令, 产品事实源, 模块文档索引, 问题求解与文档演进 and 架构取向与变更门禁.

hao-cyber/session-map · 2,889 tokens

agent-thread AGENTS.md

AGENTS.md instructions for amalshaji/agent-thread, covering agent instructions, tooling, project commands, release workflow and architecture.

amalshaji/agent-thread · 694 tokens