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/yaodub/cast/claude-mdgit clone --depth 1 https://github.com/yaodub/castWrote 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/yaodub/cast/claude-md)<a href="https://agentmods.dev/instructions/yaodub/cast/claude-md"><img src="https://agentmods.dev/badge/instructions/yaodub/cast/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 | $0.01109 | $0.01109 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
cast 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 3d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cast
Cast is a self-hosted harness for multi-user Claude Code agents that run as isolated container processes. See README.md for the project overview, philosophy, and setup.
You are reading this from a host-side Claude Code session on the Cast project (or on an agent folder under $CAST_AGENTS_DIR/ — default ~/.cast/agents/). You have the full authoring envelope: edit any package, customize agents, write services, add extensions or transports. Consoles inside Cast (Design, Configure, the All-Agents managers) operate within a constrained subset of the same docs and route work that exceeds their envelope to you. See packages/cast/manuals/MODES.md for the console-vs-advanced framing.
Repository layout
| Path | Purpose |
|---|---|
packages/cast/ |
The Cast server — orchestration, transports, identity, ACL, scheduling |
packages/agent-runner/ |
The in-container agent process (wraps the Claude Agent SDK) |
packages/ext-* |
First-party extensions (email, calendar, web-fetch, whatsapp) |
packages/extension-schema/, packages/agent-schema/, packages/admin-schema/ |
Shared schema packages |
packages/web-ui/ |
Admin and chat web UI |
~/.cast/agents/<name>/ |
A runtime agent instance — blueprint/, memory/, home/, config/, state/, ext/, sessions/. Lives outside the repo by default; override with CAST_AGENTS_DIR |
Working with agents
An agent is a folder under ~/.cast/agents/ (or whatever CAST_AGENTS_DIR resolves to). To modify an agent, edit files inside that folder; the server hot-reloads blueprint, identity, channel, and config edits on the next message. To create one, scaffold it first — admin "create agent," or pnpm agent init with CAST_AGENTS_DIR set — which provisions its identity keypair, ACL, and registration; then author on top. A bare folder is not picked up until it carries a valid manifest.json and secrets/agent.key. Service code under blueprint/service/ is the exception to hot-reload: a running service process does not reload its own source, so service-code changes need a service restart.
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.
- 3d ago First seen · 60 lines · 1,109 tokens per session scan A a3c2dd419db4
cast CLAUDE.md is an instructions file published in the GitHub repository yaodub/cast (41 stars, last pushed 11d ago), licensed MIT. It adds 1,109 tokens to every session, about $0.0055 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
orchestkit CLAUDE.md
Claude Code instructions for yonatangross/orchestkit, covering claude.md, language, tone, visuals and project overview.
orchestkit AGENTS.md
AGENTS.md instructions for yonatangross/orchestkit, covering agents.md, the one rule that prevents most broken prs, build and verify, adding a component and working conventions.
semantix CLAUDE.md
Instructions for Gnosil/semantix, covering 项目规则（claude code） and 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.