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/paultyng/ideate/claude-mdgit clone --depth 1 https://github.com/paultyng/ideateWrote 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/paultyng/ideate/claude-md)<a href="https://agentmods.dev/instructions/paultyng/ideate/claude-md"><img src="https://agentmods.dev/badge/instructions/paultyng/ideate/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 | $0.07298 | $0.07298 |
| Opus 5 | $0.03649 | $0.03649 |
| Sonnet 5 | $0.01460 | $0.01460 |
| Haiku 4.5 | $0.00730 | $0.00730 |
Grade B, and why
ideate CLAUDE.md scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Agent-mediated (MCP)** — agent sessions inherit the user's `~/.claude/settings.json` MCP servers, so any tool with an MCP server is reachable from a session without Ideate-specific glue. How it starts
The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Ideate
What This Is
Ideate is a desktop app (Wails: Go backend + web frontend) for tracking ideas through their lifecycle. v0.1 ships macOS-only; cross-platform (Linux/Windows, Intel) is on the roadmap. Phases are non-linear — an idea can start/end in any phase, skip phases, or only use one. See README.md for the user-facing overview.
Tech Stack
- Go backend via Wails v2
- React frontend in system webview (
HashRouter) - CLI: Cobra subcommands — root launches Wails app (daemon), subcommands are IPC clients
- IPC: Daemon/client via Connect (gRPC-compatible) over Unix domain socket. Proto-defined RPCs, buf for codegen.
- Local filesystem storage: each idea is a subdirectory under a user-configurable ideas directory
- Agent integration:
claudeCLI viacreack/pty(interactive PTY sessions) + Ideate MCP server + HTTP hooks - Terminal rendering: xterm.js in frontend,
creack/ptyin Go - PR review:
@git-diff-viewfor diff rendering with inline comments,ghCLI for GitHub integration
Project Structure
cmd/ideate/ # Entry point (main.go + wails.json)
proto/ideate/ipc/v1/ # Proto service definition (ipc.proto)
internal/
gen/ # Generated proto + Connect code (gitignored)
cli/ # Cobra command definitions (root, review, status)
app/ # Wails App struct, lifecycle, launch config
ipc/ # Connect server + client over Unix socket
model/ # Core types: Idea, Resource, Session, HistoryEvent
store/ # Filesystem store: read/write ideas, index management
service/ # Business-logic funnel; wraps store + coordinator for non-UI callers
agent/ # Agent coordination: PTY, session lifecycle, context injection
resource/ # Resource type registry, URL resolution, validation
mcp/ # Ideate MCP server: resource management tools for Claude sessions
hooks/ # HTTP handler for Claude Code hook events
frontend/ # Web frontend (React, HashRouter)
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 · 445 lines · 7,298 tokens per session scan B 8f06e09450f7
ideate CLAUDE.md is an instructions file published in the GitHub repository paultyng/ideate (9 stars, last pushed 17d ago), licensed MIT. It adds 7,298 tokens to every session, about $0.0365 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
wayland CLAUDE.md
Claude Code instructions for FerroxLabs/wayland, a project described as: Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
Herdforge CLAUDE.md
Claude Code instructions for Kampe/Herdforge, covering claude.md - build bootstrap & routing protocol, 1. quick invariants (hard rules), 2. fast commands, build binary and run preflight, unit tests, and build.
psyche-build AGENTS.md
AGENTS.md instructions for OpenCoven/psyche-build, covering psyche build agent guide, repository role, planning and evidence contract, canonical routing and deterministic entrypoints.
TitanX AGENTS.md
Instructions for CES-Ltd/TitanX, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
OblivionisAgent AGENTS.md
AGENTS.md instructions for RudAns/OblivionisAgent: 本仓库面向 AI 代理 / 编码助手（Claude Code · Codex · Cursor · …）的规范，单一事实源是 CLAUDE.md——别再另起一份会逐渐漂移的规则。任何 agent 进来，先读它。.
TitanX CLAUDE.md
Instructions for CES-Ltd/TitanX, a project described as: Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain memory, LangSmith traces, NemoClaw security, OpenTelemetry, and 20+ LLM providers.