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 skills add PaulRBerg/agent-skills --skill cli-castgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/cli-cast)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/cli-cast"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/cli-cast/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulrberg/agent-skills/cli-cast"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/cli-cast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.04668 |
| Opus 5.5 | $0.00019 | $0.01867 |
| Sonnet 5.5 | $0.00009 | $0.00934 |
| Haiku 4.5 | $0.00005 | $0.00467 |
Grade A, and why
cli-cast 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 28d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry Cast CLI
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Separate read, preparation, simulation, signing, and broadcast. Do not hide state-changing actions inside command construction.
For EIP-7702 authorization or delegation revocation, read references/eip7702.md before preparation. It defines signer selection, authority versus transaction sender, and conditional staged approval. It also defines authorization verification in addition to the transaction receipt.
Resolve Chain and Provider
Invoke $evm-atlas before every network operation. It owns chain resolution, discrete reads, and bounded live
subscriptions. Pass the explicit chain name or ID, JSON-RPC method, exact parameters or call object, and block selector
or checkpoint requirement. State why you need the result. Require its read packet containing the resolved chain name and
ID, provider route, result, observed block or checkpoint, and coverage gaps.
If the chain is absent from evm-atlas, stop RPC-dependent work. Do not accept an arbitrary RPC URL to bypass that
restriction. When the chain is ambiguous, never infer Ethereum.
Use an RPC URL in this skill only for a trace, fork, or send flow you cannot express as bounded discrete reads. For
RouteMesh-backed continuous transport, first require evm-atlas to confirm current RouteMesh coverage. Then, if the
explicit Foundry alias is configured, use it:
ROUTEMESH_CHAIN_ID="$CHAIN_ID" cast COMMAND --rpc-url routemesh
The alias can interpolate an environment variable, such as ROUTEMESH_API_KEY. The routemesh CLI keeps its own key.
Thus, successful atlas reads do not prove that the alias resolves. Before you sign a transaction for alias broadcast, or
use the alias in another way, run ROUTEMESH_CHAIN_ID="$CHAIN_ID" cast chain-id --rpc-url routemesh 2>/dev/null.
Require the expected chain ID. If the check fails, load the missing variable from the user's environment setup without
printing it. If you cannot load it, treat the alias as not configured.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 28d ago Changed · +6 lines 58e419798dc8
- 1mo ago Changed · +3 lines 4940c169f9e6
- 1mo ago Changed · +1 lines f194edab6059
- 1mo ago Changed · +57 lines · +2 tokens per session 8f43d0f554d5
- 1mo ago Changed · +12 lines 75a5e2c801ea
- 1mo ago Changed · +5 lines b839c7ce4bbc
- 1mo ago Changed · +7 lines abc6b57aad20
- 1mo ago Changed · +5 lines 6fa9de0dba69
- 1mo ago Changed · +24 lines 9314cb1c8287
- 1mo ago First seen · 207 lines · 45 tokens per session scan A 17186e1253a2
cli-cast is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 4,668 once invoked, about $0.0002 per session on Opus 5.5. 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.
cli-cast compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cli-castPaulRBerg/agent-skills | Skill | 104 | 2d ago | MIT | A | 47 | Claude Code, Codex |
| signature-replayPurpleAILAB/Decepticon | Skill | 6.6k | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | 2d ago | MIT | A | 13 | Claude Code, Codex |
| official-sui-skillsMystenLabs/sui | Skill | 7.8k | yesterday | Apache-2.0 | A | 116 | Claude Code, Codex |
| onchainkitalsk1992/CloddsBot | Skill | 3.1k | 2d ago | MIT | A | 24 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | 2d ago | MIT | A | 11 | Claude Code, Codex |
| devtools-event-clientTanStack/devtools | Skill | 512 | yesterday | MIT | A | 79 | Claude Code, Codex |