A way to delegate complex programming work to Claude Code, an AI coding assistant, through shell commands that run without its interactive screen.

It helps hand off feature work, bug fixes, refactoring, tests, code reviews, migrations, and other multi-step repository changes.

It provides a fallback when Codex is unavailable, not signed in, unsuitable for the task, or explicitly not wanted.

claude-code — Skill by ldclabs

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 skills/ldclabs/anda-bot/claude-code

Any agent

npx skills add ldclabs/anda-bot --skill claude-code

Clone the repo

git clone --depth 1 https://github.com/ldclabs/anda-bot

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00095	$0.01781
Opus 5	$0.00048	$0.00890
Sonnet 5	$0.00019	$0.00356
Haiku 4.5	$0.00010	$0.00178

Measured 2d ago against content hash 767ec3cdc759, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code 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 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.

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.

skills/claude-code/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code CLI Delegation for Agent's Shell Tool

This skill is written for shell tool. Assume there is no PTY. Do not use the interactive Claude TUI.

Selection Policy

Codex is preferred for programming delegation. Before invoking Claude Code, check whether Codex can handle the task:

if command -v codex >/dev/null 2>&1 && codex login status >/dev/null 2>&1; then
  echo "Prefer the codex skill for this coding task."
elif command -v claude >/dev/null 2>&1; then
  claude --version
  claude auth status --text
else
  echo "Neither codex nor claude is installed; continue directly or ask the user to install one."
fi

Use Claude Code when:

codex is not installed or not authenticated.
Codex failed on a task where a second coding agent is useful.
The user explicitly asks for Claude Code.
The repo or task is already configured around Claude Code conventions.

If claude auth status --text fails, ask the user to run claude auth login, claude auth login --console, or configure ANTHROPIC_API_KEY. Do not start an interactive login flow from the agent.

Non-Interactive Rules

Use claude -p for every delegated task.
Do not run bare claude, claude "query", tmux, slash commands, /review, /compact, interactive permission flows, or anything that waits for keyboard input.
Do not use --tmux, -w --tmux, or PTY orchestration from older Claude Code guides.
Pass the task through stdin or a carefully quoted prompt. Stdin is safer for long task descriptions.
Set --max-turns so the agent cannot run indefinitely.
Use --allowedTools to make non-interactive tool use explicit. Keep tools narrower for review-only work.
Avoid --dangerously-skip-permissions unless the user explicitly approves a fully trusted run.

Preflight Checklist

Before delegating:

Identify the project root: git rev-parse --show-toplevel 2>/dev/null || pwd.
Check git status --short and preserve unrelated user changes.
Turn the user's request into clear success criteria, constraints, and verification commands.
Choose the tool list: broad for implementation, read-only for review.
Prefer Codex if it is available and authenticated.

Read the full file on GitHub · 164 lines

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.

2d ago First seen · 164 lines · 95 tokens per session scan A 767ec3cdc759

Subscribe to this mod's changes

claude-code is a skill published in the GitHub repository ldclabs/anda-bot (23 stars, last pushed 25d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,781 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.

Building agents

agent-messaging

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

davila7/claude-code-templates · 64 tokens

kagent-dev

Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.

kagent-dev/kagent · 65 tokens

workflows

Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.

get-bb/bb · 47 tokens

claude-code