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/pyros-projects/beads-viz/agents-mdgit clone --depth 1 https://github.com/pyros-projects/beads-vizWrote 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/pyros-projects/beads-viz/agents-md)<a href="https://agentmods.dev/instructions/pyros-projects/beads-viz/agents-md"><img src="https://agentmods.dev/badge/instructions/pyros-projects/beads-viz/agents-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 5.1 | $0.01897 | $0.01897 |
| Opus 5 | $0.00949 | $0.00949 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
beads-viz 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Beads Viz
Read-only task graph visualizer for Claude Desktop. MCP server (TypeScript/Node.js) wrapping the bd CLI, with a Svelte single-file UI bundle showing interactive DAG visualization, list view, and stats dashboard. Runs inside Claude Desktop as an MCP App (sandboxed iframe).
Quick Start
npm install
npm run build # Build UI bundle + server
npm run dev # Vite dev server (UI only, no MCP host)
Claude Desktop Configuration
Add to ~/.config/claude-desktop/config.json:
{
"mcpServers": {
"beads-viz": {
"command": "node",
"args": ["dist/server/index.js"],
"cwd": "/path/to/your/beads-project"
}
}
}
The server discovers the Beads project by walking up from cwd to find .beads/config.yaml.
Architecture
Claude Desktop (MCP Host)
├── Chat conversation
│ "Show me the task graph"
│ → calls visualize-tasks tool
├── MCP Server (Node.js, stdio)
│ ├── visualize-tasks → bd list --all --json → summary + tasks + ui ref
│ ├── poll-tasks (app-only) → bd list --all --json → fresh data
│ ├── show-task (app-only) → bd show <id> --json → task detail
│ └── ui://beads-viz resource → serves dist/index.html
└── Sandboxed iframe (MCP App)
├── Top Strip (project, stats pills, DAG/LIST/STATS tabs)
├── Canvas (DAG / List / Stats views)
├── Bottom Drawer (task detail on click)
└── Polls server every 3s for fresh data
Key insight: The UI is read-only. All task mutations (claim, close, create) happen through the agent chat, not the UI.
Project Structure
src/
├── server/ # MCP server (Node.js target)
│ ├── index.ts # Entry point: McpServer + stdio transport
│ ├── tools.ts # Tool registrations (visualize, poll, show)
│ ├── beads-client.ts # bd CLI wrapper (execFile + JSON parse)
│ └── types.ts # Server-side TypeScript types
└── ui/ # Svelte app (browser target, Vite-bundled)
├── App.svelte # Root: view switching, layout, keyboard
├── main.ts # Svelte mount + MCP bridge init
├── app.css # CSS variables, reset, animations
├── index.html # Vite entry point
├── components/
│ ├── TopStrip.svelte # 32px strip: project, stats, tabs
│ ├── DagView.svelte # ELK.js DAG canvas + SVG edges
│ ├── DagNode.svelte # 156x42 node card with phase colors
│ ├── ListView.svelte # Status-grouped task list
│ ├── StatsView.svelte # Progress ring, phase bars, velocity
│ └── TaskDrawer.svelte # Bottom drawer with task details
└── lib/
├── elk-layout.ts # ELK.js layout computation
├── phase.ts # 9-phase color system (dark + light)
├── stores.ts # Svelte writable stores
├── mcp-bridge.ts # MCP App SDK bridge (connect, poll, theme)
└── types.ts # UI-side TypeScript types
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.
- 4d ago First seen · 165 lines · 1,897 tokens per session scan A 57959bdd5284
beads-viz AGENTS.md is an instructions file published in the GitHub repository pyros-projects/beads-viz (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,897 tokens to every session, about $0.0095 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
linkedin-mcp-server AGENTS.md
AGENTS.md instructions for stickerdaniel/linkedin-mcp-server, covering claude.md, development commands, scraping rules, browser identity rules and profile safety rules.
pagespeed-insights-mcp AGENTS.md
AGENTS.md instructions for ruslanlap/pagespeed-insights-mcp, covering project rules — pagespeed-insights-mcp (mcp server), специфіка проєкту, обов'язкові практики (mcp + ts), serena + .serena/ and професійні skills тільки.
kafka-schema-reg-mcp AGENTS.md
AGENTS.md instructions for aywengo/kafka-schema-reg-mcp, covering development guidelines, prerequisites, quick setup, install dependencies and install dev dependencies (optional but recommended).
ls-mcp AGENTS.md
AGENTS.md instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.
PBP CLAUDE.md
Claude Code instructions for MadGapun/PBP, covering pbp — claude-code-memory, stand 2026-08-25 (v1.7.23 stable) — ehrliche zahlen, stand 2026-07-16 (v1.8.0-beta.6, prerelease) — hotfix #760, stand 2026-07-14 (v1.7.7) — scoring-fairness & praxis-funde and stand 2026-07-03 (v1.7.6) — alltags-fuehrung.
mcp-standardnotes CLAUDE.md
Claude Code instructions for lozit/mcp-standardnotes, covering mcp standard notes, stack, commands, structure and exposed mcp tools.