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/warpforgehq/warpforge/claude-mdgit clone --depth 1 https://github.com/warpforgehq/warpforgeWrote 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/warpforgehq/warpforge/claude-md)<a href="https://agentmods.dev/instructions/warpforgehq/warpforge/claude-md"><img src="https://agentmods.dev/badge/instructions/warpforgehq/warpforge/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 | $0.02927 | $0.02927 |
| Opus 5 | $0.01463 | $0.01463 |
| Sonnet 5 | $0.00585 | $0.00585 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade A, and why
warpforge CLAUDE.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 today.
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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: Warpforge
Workspace orchestrator with TUI and desktop interfaces. Manages multiple dev projects: isolated services with auto-resolved ports, embedded agent terminals (Codex, Claude), instant context switching.
Architecture
Core (Rust):
- Language: Rust
- Async runtime: Tokio
- Daemon: Background process that manages services, agents, and project state
- PTY:
portable-pty— real TTY for spawned agents - Terminal emulation:
vt100crate — parses ANSI into screen buffer - CLI:
clapderive API - Config:
.warpforge/workspace.yamlper project (serde_yaml; legacy root-level.warpforge.yaml/.wf.yaml/.workspace.yamlstill load), registry in~/.warpforge/projects.json - Port isolation: each project gets 100-port range (4000+),
${svc.port}interpolation in env vars - Daemon IPC: WebSocket JSON-RPC (port 61814)
TUI (Rust):
- Framework: Ratatui + Crossterm
- Binary:
cargo build --release→target/release/warpforge - Key crates: ratatui 0.29, crossterm 0.28 (event-stream), vt100 0.15
Desktop (TypeScript + Tauri):
- Framework: Tauri v2 (Rust shell + WebView)
- Frontend: React 18 + TypeScript + Vite
- UI: Tailwind CSS + Radix UI primitives + shadcn/ui components
- State: Zustand (persisted to localStorage)
- Terminal: CodeMirror for editor (interactive terminal not yet implemented)
- Package manager: Bun
- Linting: oxlint + oxfmt
- Tests: Vitest + React Testing Library
Key crates (Rust): tokio, clap 4, serde, anyhow, portable-pty 0.8, vt100 0.15, ratatui 0.29, crossterm 0.28
Source layout (src/)
main.rs — CLI entry (clap), subcommands: add, remove, list, ui
app.rs — TUI event loop (tokio::select), AppState, InputMode (Navigate/Terminal), key handling
agent.rs — AgentManager: PTY spawn via portable-pty, vt100 parser, input/output channels
service.rs — ServiceManager: sh -c spawn, stdout/stderr log capture, process-group kill, port allocation
config.rs — workspace config parsing + auto-detect (package.json scripts, docker-compose)
workflow_config.rs — .warpforge/workflows/*.yaml templates: schema, validation, prompt rendering
registry.rs — ~/.warpforge/projects.json CRUD
ports.rs — Port range allocation (4000+), ${svc.port} env interpolation
tui/
mod.rs — render dispatch (Dashboard vs Project screen)
dashboard.rs — Project list with service/agent status, j/k nav, Enter to open
project.rs — Split layout: sidebar (services + agents) + right pane (terminal or logs)
terminal.rs — TerminalPane widget: vt100 Screen → ratatui Buffer (cell-by-cell, colors, cursor)
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.
- today Changed · +34 lines · +418 tokens per session aeed1840500f
- 4d ago First seen · 198 lines · 2,509 tokens per session scan A bb5e2ca4fe0c
warpforge CLAUDE.md is an instructions file published in the GitHub repository warpforgehq/warpforge (30 stars, last pushed 2d ago), licensed MIT. It adds 2,927 tokens to every session, about $0.0146 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 2026-08-30.
Other instructions, from other repositories
ORG2 AGENTS.md
AGENTS.md instructions for org2AI/ORG2, covering agents.md — agent skill routing for orgii, skill routing table, root-cause-first bug fixing, default delivery flow and ui copy conventions.
ankaloop AGENTS.md
AGENTS.md instructions for tao12345666333/ankaloop, covering ankaloop project rules, project overview, code style, architecture patterns and agent behavior.
little-coder AGENTS.md
Instructions for itayinbarr/little-coder, covering little-coder, capabilities & autonomy, runtime invariants, available tools and file & shell.
elon-stack copilot-instructions.md
Copilot instructions for AccountZero/elon-stack, covering copilot instructions, coding discipline, 1. think before coding, 2. simplicity first and 3. surgical changes.
elon-stack AGENTS.md
AGENTS.md instructions for AccountZero/elon-stack, covering agents.md, coding discipline, 1. think before coding, 2. simplicity first and 3. surgical changes.
elon-stack CLAUDE.md
Claude Code instructions for AccountZero/elon-stack, covering claude.md, coding discipline, 1. think before coding, 2. simplicity first and 3. surgical changes.