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 skills/yaodub/cast/cast-buildnpx skills add yaodub/cast --skill cast-buildgit 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/skills/yaodub/cast/cast-build)<a href="https://agentmods.dev/skills/yaodub/cast/cast-build"><img src="https://agentmods.dev/badge/skills/yaodub/cast/cast-build.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 | $0.00096 | $0.01620 |
| Opus 5 | $0.00048 | $0.00810 |
| Sonnet 5 | $0.00019 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
cast-build 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cast — advanced-mode authoring (agent-folder scope)
You are Claude Code in Cast's authoring lane. The operator wants you to write or change code inside one or more agent folders. Every diff you propose is reviewed line-by-line; that review is the only safety property.
Scope
Argument: <folder> (optional).
- With folder → anchor at
$CAST_AGENTS_DIR/<folder>/(default~/.cast/agents/<folder>/). Treat the cast repo as read-only context. - Without folder → cross-agent folder operations across
$CAST_AGENTS_DIR/(rename, restore from backup, bulk delete, etc.). - New agent → scaffold it first (admin "create agent," or
pnpm agent init), which provisions the identity keypair, ACL, and registration; then author its blueprint and service. Don't hand-create a bare folder — the server ignores it until it carries a validmanifest.json+secrets/agent.key, and itsAGENTS_DIRreconciler only registers a folder that is already complete when it appears.
If neither $CAST_AGENTS_DIR nor a folder hint is present, ask the operator before guessing.
What you author
| Layer | Examples | Reload after edit |
|---|---|---|
| Blueprint identity | blueprint/identity/{prompt,whoami,peers,skills}.md |
agent__expire_conversations |
| Channels | blueprint/channels/<name>/{channel.json,prompt.md,bootstrap.md,cleanup.md} |
agent__expire_conversations |
| Capabilities (extension wiring) | blueprint/props/capabilities.json — toggling extensions on/off, configuring already-registered extensions |
configure__restart_agent_service for tool-list changes; agent__expire_conversations for config-only |
| Schedules | blueprint/props/schedule.txt, blueprint/props/settings.json |
Auto hot-reload |
| Assets | blueprint/assets/* (static files mounted at /assets) |
None |
| Per-agent service code | blueprint/service/* (the host process for this one agent) |
configure__restart_agent_service (interrupts in-flight conversations) |
| Operator config | config/agent.json, config/acl.json, config/provisions.json, config/transport.json |
File-watched (most fields); restart for model changes |
| Extension operator config | config/ext/<name>/.env, config/ext/<name>/config.json |
configure__restart_agent_service on secret rotation |
| Cross-agent folder ops | rename, restore from backup, bulk delete under $CAST_AGENTS_DIR/ |
n/a |
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.
- 5d ago First seen · 62 lines · 96 tokens per session scan A ef21cbd77679
cast-build is a skill published in the GitHub repository yaodub/cast (41 stars, last pushed 13d ago), licensed MIT. It adds 96 tokens to every session and 1,620 once invoked, about $0.0005 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 skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
semantix-guide
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…
largest-files-finder
List the top 3 largest files in a given directory.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
cross-border-customer-service-brief
Cluster refund, return, complaint, and bad-review notes into a daily support brief with response guidance and escalation hints.
cross-border-price-match-review
Cluster competitor price, coupon, shipping, and bundle observations into a price-gap review with explicit human-approval guidance.