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 raulvidis/openclaw-multi-agent-kit --skill acpx-sessiongit clone --depth 1 https://github.com/raulvidis/openclaw-multi-agent-kitWrote 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/raulvidis/openclaw-multi-agent-kit/acpx-session)<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/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/raulvidis/openclaw-multi-agent-kit/acpx-session"><img src="https://agentmods.dev/badge/skills/raulvidis/openclaw-multi-agent-kit/acpx-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 9 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00042 | $0.01067 |
| Opus 5.5 | $0.00017 | $0.00427 |
| Sonnet 5.5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00107 |
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 1mo 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 — 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:
- Receive a
HANDOFFmessage viasessions_send - Spawn an ACPX session for the target coding agent
- Post
ACKwith the session name and ETA - On completion, post
DONEwith evidence back viasessions_send - If blocked, post
BLOCKEDwith explicit unblock requirements
This bridges the inter-agent handoff protocol with ACPX session management.
Operating Rules
When to use which mode:
mode: persistentfor 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.execfor stateless, one-shot work (a single read, a one-prompt summary, a quick syntax fix). No session is retained. Always preferexecwhen the task fits in one prompt and doesn't need memory of prior turns.
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.
- 1mo ago First seen · 147 lines · 42 tokens per session scan A 506bd02379ef
acpx-session is a skill published in the GitHub repository raulvidis/openclaw-multi-agent-kit (396 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,067 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…