acpx-session

acpx-session is a skill for Claude Code, Codex from raulvidis/openclaw-multi-agent-kit. It costs 42 tokens per session (1,067 once invoked), scanned A, original, MIT.

A command-line workflow for assigning tasks from one AI agent to coding agents. It supports named sessions, separate workstreams, one-off tasks, status checks, and cancellation.

In plain words
What is it for?
Use it to start and name agent sessions, send prompts or task files, run concurrent frontend and backend work, check progress, and cancel work.
Why use it?
It keeps delegated coding work organised and preserves context for ongoing tasks, while allowing independent tasks to run in parallel.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions subagents; mentions Codex; built for openclaw.

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/raulvidis/openclaw-multi-agent-kit/acpx-session
Any agent
npx skills add raulvidis/openclaw-multi-agent-kit --skill acpx-session
Clone the repo
git clone --depth 1 https://github.com/raulvidis/openclaw-multi-agent-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for acpx-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/raulvidis/openclaw-multi-agent-kit/acpx-session.svg)](https://agentmods.dev/skills/raulvidis/openclaw-multi-agent-kit/acpx-session)
Your own site
<a href="https://agentmods.dev/skills/raulvidis/openclaw-multi-agent-kit/acpx-session"><img src="https://agentmods.dev/badge/skills/raulvidis/openclaw-multi-agent-kit/acpx-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,067 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 5.1 $0.00042 $0.01067
Opus 5 $0.00021 $0.00534
Sonnet 5 $0.00008 $0.00213
Haiku 4.5 $0.00004 $0.00107

Measured 7d ago against content hash 506bd02379ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

acpx-session 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 7d 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.

templates/skills/acpx-session/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install

Copy to agents/<coder>/skills/acpx-session/SKILL.md. Requires ACPX CLI installed and at least one coding agent configured.

ACPX Session Skill

Session Creation

Create a new session for a coding agent:

acpx <agent> sessions new

Named sessions for tracking:

acpx <agent> sessions new --name <name>

Prompt Submission

Send a task to the agent:

acpx <agent> "task description"

Submit from a file:

acpx <agent> --file <path>

Pipe via stdin:

echo "task" | acpx <agent>

Parallel Workstreams

Use named sessions to run concurrent work without collisions:

acpx <agent> -s frontend "implement login page"
acpx <agent> -s backend "add auth endpoint"

Each named session maintains independent context and state.

Exec Mode

For one-shot, stateless tasks that don't need session persistence:

acpx <agent> exec "one-shot task"

No session is created or retained after completion.

Status and Cancel

Check active sessions:

acpx <agent> status

Cancel a running session:

acpx <agent> cancel

Cancel a named session:

acpx <agent> cancel -s <name>

Integration with sessions_send

Combine ACPX with the handoff protocol:

  1. Receive a HANDOFF message via sessions_send
  2. Spawn an ACPX session for the target coding agent
  3. Post ACK with the session name and ETA
  4. On completion, post DONE with evidence back via sessions_send
  5. If blocked, post BLOCKED with explicit unblock requirements

This bridges the inter-agent handoff protocol with ACPX session management.

Operating Rules

When to use which mode:

  • mode: persistent for any task that spans more than one prompt or needs the coding agent to remember context (refactors, multi-file changes, anything with iteration). Cost: a live session per topic.
  • exec for stateless, one-shot work (a single read, a one-prompt summary, a quick syntax fix). No session is retained. Always prefer exec when the task fits in one prompt and doesn't need memory of prior turns.

Read the full file on GitHub · 147 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. 7d ago First seen · 147 lines · 42 tokens per session scan A 506bd02379ef

Subscribe to this mod's changes

acpx-session is a skill published in the GitHub repository raulvidis/openclaw-multi-agent-kit (394 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,067 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens