What is agentpulse AGENTS.md?

Project-specific instructions for AgentPulse, an application that monitors and manages coding-agent sessions. They describe its technology stack, folder structure, architecture, and common development commands.

Use them when modifying AgentPulse, running its development or production commands, checking code quality, validating TypeScript, or reviewing its architecture.

They give a coding agent the context needed to work consistently in this repository instead of guessing how the application is built or checked.

How jstuart0/agentpulse configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to jstuart0/agentpulse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jstuart0/agentpulse/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jstuart0/agentpulse

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jstuart0/agentpulse/agents-md/github.svg)](https://agentmods.dev/instructions/jstuart0/agentpulse/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jstuart0/agentpulse/agents-md"><img src="https://agentmods.dev/badge/instructions/jstuart0/agentpulse/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jstuart0/agentpulse/agents-md"><img src="https://agentmods.dev/badge/instructions/jstuart0/agentpulse/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,538 This file is loaded in full into every session.

When invoked 2,538 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02538	$0.02538
Opus 5.5	$0.01015	$0.01015
Sonnet 5.5	$0.00508	$0.00508
Haiku 4.5	$0.00254	$0.00254

Measured 16d ago against content hash 801a874b8277, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentpulse AGENTS.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 16d 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.

AGENTS.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - AgentPulse

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. GitHub Copilot CLI is also observed (dedicated hooks, badge, "Observed only" hint) but can't be launched or steered — see LAUNCHABLE_AGENT_TYPES below.

Tech Stack

Runtime: Bun
Backend: Hono (HTTP framework)
Frontend: React 19 + Vite + TailwindCSS
State: 8 Zustand stores
Database: SQLite (default) and PostgreSQL (production / multi-replica, v0.4.0+) via Drizzle ORM — set DATABASE_URL=postgres://... to opt into Postgres
Real-time: WebSocket (native Bun) + 3s polling fallback
MCP: Model Context Protocol server in packages/agentpulse-mcp/ (agentpulse mcp serve|install); see docs/MCP.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

Project Structure

src/
  server/
    routes/       ~24 route files: ingest.ts, sessions.ts, settings.ts, auth.ts,
                  launches.ts, templates.ts, projects.ts, search.ts, setup.ts,
                  ask.ts, channels.ts, labs.ts, supervisors.ts, health.ts,
                  internal.ts, csp-report.ts, ingest-counters.ts,
                  agent-type-query.ts, ai-gates.ts, ai-inbox.ts,
                  ai-intelligence.ts, ai-providers.ts, ai-status.ts, ai-watcher.ts
    services/     ~22 service files + subdirs: ai/, ask/, channels/, projects/,
                  search/, templates/, util/, workspace/,
                  event-processor.ts, event-dedup.ts, event-dto.ts,
                  session-tracker.ts, session-ownership.ts, name-generator.ts,
                  telemetry.ts, settings-service.ts, labs-service.ts,
                  launch-dispatch.ts, launch-validator.ts, notifier.ts, ...
    db/           Drizzle schema (SQLite + Postgres, per-dialect), client, migrations
    auth/         API key auth (ingest/observe/manage scopes), forwardauth header trust middleware
    ws/           WebSocket pub/sub
  web/
    pages/        AskPage, DashboardPage, DigestPage, HostsPage, InboxPage,
                  LaunchDetailPage, LoginPage, ProjectsPage, SearchPage,
                  SessionDetailPage, SettingsPage, SetupPage, TemplatesPage
    components/   SessionCard, SessionGrid, StatusBadge, Layout, PlanTracker,
                  IntelligenceBadge, MarkdownContent, TopBar, WsStatusChip,
                  + subdirs: inbox/, session-detail/, settings/, templates/
    stores/       8 stores: connection-store, event-store, labs-store,
                  projects-store, session-store, tabs-store, ui-prefs-store,
                  user-store
    hooks/        useWebSocket, useSessions
    lib/          api.ts (single API client), utils.ts (parseDate(), etc.)
  shared/         Shared types (session-state.ts, etc.)
  supervisor/     Local supervisor process (launch/control plane)
packages/
  agentpulse-mcp/ Standalone MCP server package (publishes to npm as
                  @craze0/agentpulse-mcp; or run it from a checkout
                  via `agentpulse mcp serve`/`install`)
deploy/k8s/       Kubernetes manifests (namespace, deployment, service,
                  ingressroute, middleware, networkpolicy, backup PVC, etc.)
deploy/overlays/postgres/  Kustomize overlay for Postgres-backed deployments
scripts/          setup-relay.sh, setup-hooks.sh, relay.ts, install-local.sh,
                  install-local.ps1, build-and-push.sh, statusline.sh,
                  check-installers.ts, smoke-parsers.ts, ai-live-test.ts
snippets/         CLAUDE.md/AGENTS.md snippets for semantic status reporting
telemetry-worker/ Cloudflare Worker for anonymous telemetry collection

Read the full file on GitHub · 177 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.

16d ago Changed · -2 tokens per session 801a874b8277
25d ago Changed 798b67f98190
28d ago Changed · +4 tokens per session dc62c3a5536b
29d ago Changed · +25 lines · +809 tokens per session e46396b012da
1mo ago First seen · 152 lines · 1,727 tokens per session scan A 43ae92d40c9f

Subscribe to this mod's changes

agentpulse AGENTS.md is an instructions file published in the GitHub repository jstuart0/agentpulse (25 stars, last pushed 4d ago), licensed MIT. It adds 2,538 tokens to every session, about $0.0102 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 2026-08-30.

Claude Code ai-agents ai-tooling bun codex-cli homelab

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).

microsoft/vscode · 9,715 tokens

agentpulse: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md - AgentPulse

Tech Stack

Commands

Project Structure

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md