subagent-cli

A way to run separate AI coding agents as non-interactive command-line programs. It supports agents such as Codex, Cursor Agent, or Claude when the surrounding execution setup provides them.

In plain words
What is it for?
Use it to offload implementation, code review, investigations, or work that needs another agent to edit and inspect a project.
Why use it?
It makes it possible to delegate complex coding, review, or multi-file work without interacting with each agent step by step.

Skill for Claude CodeCodex

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/xuiltul/animaworks/subagent-cli
Any agent
npx skills add xuiltul/animaworks --skill subagent-cli
Clone the repo
git clone --depth 1 https://github.com/xuiltul/animaworks

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,822 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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.02822
Opus 5 $0.00026 $0.01411
Sonnet 5 $0.00010 $0.00564
Haiku 4.5 $0.00005 $0.00282

Measured yesterday against content hash 6a7133bcf655, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-cli 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 yesterday.

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.

templates/en/common_skills/subagent-cli/SKILL.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

subagent-cli

Run external AI agent CLIs as subprocesses via Bash to delegate complex coding tasks. Use as a "power tool" to extend execution capability while keeping your identity, judgment, and memory.

Relationship with Framework Execution Modes

This skill applies only when the Bash tool is available.

Mode Implementation Bash Skill Applicability
Mode S agent_sdk.py (Claude Agent SDK) Available by default Applies. Read/Write/Edit/Bash/Grep/Glob/WebFetch/WebSearch available
Mode C codex_sdk.py (Codex SDK) Depends on Codex CLI toolset codex exec not needed — Framework runs Codex directly. cursor-agent / claude -p can be invoked via Bash (when Bash is available)
Mode D Cursor Agent (cursor-agent subprocess) Depends on Cursor CLI toolset cursor-agent -p not needed — Framework runs cursor-agent directly. MCP integration. Tool access similar to Mode S but via the cursor-agent binary. codex exec / claude -p can be invoked via Bash (when Bash is available)
Mode G Gemini CLI (gemini subprocess) Depends on Gemini CLI toolset Manual gemini invocation not needed — Framework runs it directly. MCP integration, stream-json output. Other CLIs can be invoked via Bash (when Bash is available)
Mode A/B LiteLLM + tool_use / 1-shot Only when permitted in permissions.json Applies if Bash is permitted

Important: For Mode C (codex/*), Mode D (cursor/*), and Mode G (gemini/*), the framework runs each engine directly. You do not need to call codex exec (Mode C), cursor-agent -p (Mode D), or the Gemini CLI (Mode G) from Bash yourself. Refer to the relevant sections only when you explicitly want a different CLI (cursor-agent, claude -p, codex exec, etc.).

Windows exception: On native Windows, if shell execution becomes policy blocked, or codex exec exited with code 1 keeps recurring, stop retrying local codex exec. For shell-required tasks, use machine as the standard fallback with engine=claude and an explicit working_directory.

Read the full file on GitHub · 352 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.

  1. yesterday First seen · 352 lines · 52 tokens per session scan A 6a7133bcf655

Subscribe to this mod's changes

subagent-cli is a skill published in the GitHub repository xuiltul/animaworks (254 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,822 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.x-automation

Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…

aden-hive/hive · 81 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.writing-hive-skills

Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.

aden-hive/hive · 63 tokens