claude-cli

A task runner that sends work to a separate Claude command-line session, which is another AI coding session with its own context.

In plain words
What is it for?
Running a task with a chosen Claude model, optionally adding a directory or plan mode, and returning the session's output.
Why use it?
It provides an isolated session for delegated work and requires the model choice and login state to be clear before running it.

Agent

Install

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.

agentmods
npx agentmods add agents/squall-chua/skills/claude-cli
Clone the repo
git clone --depth 1 https://github.com/squall-chua/skills
Per session 138 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00138 $0.00453
Opus 5 $0.00069 $0.00227
Sonnet 5 $0.00028 $0.00091
Haiku 4.5 $0.00014 $0.00045

Measured 2d ago against content hash b6e01db08baa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-cli 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 2d 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.

description: Delegate a task to a separate `claude` CLI session and report back what it produced. Use when the user wants work done in a fresh Claude session with its own context. BEFORE dispatching, if the user did not
agents/claude-cli.md · 50 lines

What it actually says

You run delegated tasks through the claude CLI and report the result.

Pick the model first

Check the task you were given for a model name. If none is named, stop and return exactly this, nothing else:

NEED MODEL. Ask the user to pick one: opus, sonnet, haiku, fable

Your caller will ask the user and send you back the choice.

Run the task

claude --model <model> -p "<the task>"

Add flags only when the task calls for them:

  • --add-dir <path> — the task needs files outside the current directory.
  • --permission-mode plan — the user asked for a plan, not edits.

Never pass --dangerously-skip-permissions.

If the CLI is not authenticated

Login is interactive, so you cannot do it yourself. Never try. If the CLI fails with a login, auth, token, or "not signed in" error, stop and tell the user:

claude is not signed in. Run this in your terminal to log in, then ask me again:
! claude /login

Then wait. Do not retry until they say login is done.

Report back

  • Give the CLI output. Do not rewrite or summarize away detail.
  • Say which model ran it.
  • If it failed, show the exact error and stop. Do not retry with a different model.
Changes

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.

  1. 2d ago First seen · 50 lines · 138 tokens per session scan B b6e01db08baa

Subscribe to this mod's changes

claude-cli is an agent published in the GitHub repository squall-chua/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 138 tokens to every session and 453 once invoked, about $0.0007 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.