Skills Plugins MCP Prompt Model 博客 我的中心

acpx

Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge.

DeepseekModel Curated skill Quality Excellent · 90 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=openclaw-acpx-skills-acpx-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name acpx description Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge. acpx When to use this skill Use this skill when you need to run coding agents through acpx , manage persistent ACP sessions, queue prompts, override the Claude system prompt, prune stale sessions, consume structured agent output from scripts, or compose multi-agent workflows declaratively with acpx/flows . What acpx is acpx is a headless, scriptable CLI client for the Agent Client Protocol (ACP). It is built for agent-to-agent communication over the command line and avoids PTY scraping. Core capabilities: Persistent multi-turn sessions per repo/cwd One-shot execution mode ( exec ) Named parallel sessions ( -s/--session ) Idempotent session creation ( sessions ensure ) Session retention controls ( sessions prune with age filters and history cleanup) Portable session export/import for moving records and history across machines Queue-aware prompt submission with optional fire-and-forget ( --no-wait ) Cooperative cancel command ( cancel ) for in-flight turns Graceful cancellation via ACP session/cancel on interrupt Session control methods ( set-mode , set <key> <value> ) Agent reconnect/resume after dead subprocess detection Prompt input via stdin or --file Config files with global+project merge and config show|init Session metadata/history inspection ( sessions show , sessions history ) Local agent process checks via status Stable ACP client methods for filesystem and terminal requests Stable ACP authenticate handshake via env/config credentials Structured streaming output ( text , json , quiet ) with optional --suppress-reads Prompt-response _meta preservation across direct, queued, compare, and embedded-runtime results Built-in agent registry plus raw --agent escape hatch Claude system prompt override via --system-prompt / --append-system-prompt Optional ACP filesystem and terminal capability opt-outs via --no-fs and --no-terminal Tool whitelist ( --allowed-tools ), turn cap ( --max-turns ), retry on transient failures ( --prompt-retries ) Multi-agent flows via acpx flow run and the acpx/flows authoring API ( defineFlow , decision , decisionEdge , acp , action , compute , checkpoint ) Install npm i -g acpx For normal session reuse, prefer a global install over npx . Command model prompt is the default verb. acpx [global_options] [prompt_text...] acpx [global_options] prompt [prompt_options] [prompt_text...] acpx [global_options] exec [prompt_options] [prompt_text...] acpx [global_options] compare <agent>... '<prompt_text>' acpx [global_options] compare <agent>... --file <path> acpx [global_options] cancel [-s <name>] acpx [global_options] set-mode <mode> [-s <name>] acpx [global_options] set <key> <value> [-s <name>] acpx [global_options] status [-s <name>] acpx [global_options] sessions [list | new [--name <name>] | ensure [--name <name>] | close [name] | show [name] | history [name] [-- limit <count>] | export [name] --output <path> | import <archive> [--name <name>] [--cwd < dir >] | prune [--dry-run] [--before < date > | --older-than <days>] [--include-history]] acpx [global_options] config [show | init] acpx [global_options] flow run <file> [--input-json '<json>' | --input-file <path>] [--default-agent <name>] acpx [global_options] <agent> [prompt_options] [prompt_text...] acpx [global_options] <agent> prompt [prompt_options] [prompt_text...] acpx [global_options] <agent> exec [prompt_options] [prompt_text...] acpx [global_options] <agent> cancel [-s <name>] acpx [global_options] <agent> set-mode <mode> [-s <name>] acpx [global_options] <agent> set <key> <value> [-s <name>] acpx [global_options] <agent> status [-s <name>] acpx [global_options] <agent> sessions [list | new [--name <name>] | ensure [--name <name>] | close [name] | show [name] | history [name] [-- limit <count>] | export [name] --output <path> | import <archive> [--name <name>] [--cwd < dir >] | prune [--dry-run] [--before < date > | --older-than <days>] [--include-history]] If prompt text is omitted and stdin is piped, acpx reads prompt text from stdin. Built-in agent registry Friendly agent names resolve to commands: pi -> npx pi-acp openclaw -> openclaw acp codex -> npx -y @agentclientprotocol/codex-acp (ACPX-owned package range) claude -> npx -y @agentclientprotocol/claude-agent-acp (ACPX-owned package range) gemini -> gemini --acp cursor -> cursor-agent acp copilot -> copilot --acp --stdio droid -> droid exec --output-format acp ( factory-droid and factorydroid also resolve to droid ) fast-agent -> uvx fast-agent-mcp acp grok-build -> grok agent stdio iflow -> iflow --experimental-acp kilocode -> npx -y @kilocode/cli acp kimi -> kimi acp kiro -> kiro-cli-chat acp mcode -> mcode acp (install/authenticate MCode first; prefer exec for one-shot work, and require advertised ACP reload support for cross-invocation continuity) mux -> mux acp via an ACPX-owned npm range opencode -> npx -y opencode-ai acp pool -> pool acp qoder -> qodercli --acp Forwards Qoder-native --allowed-tools and --max-turns startup flags from acpx session options. qwen -> qwen --acp trae -> traecli acp serve zeroclaw -> zeroclaw acp Rules: Default agent is codex for top-level prompt , exec , and sessions . Unknown positional agent tokens are treated as raw agent commands. --agent <command> explicitly sets a raw ACP adapter command. Do not combine a positional agent and --agent in the same command. Commands Prompt (default, persistent session) Implicit: acpx codex 'fix flaky tests' Explicit: acpx codex prompt 'fix flaky tests' acpx prompt 'fix flaky tests' # defaults to codex Behavior: Uses a saved session for the session scope key Auto-resumes prior session when one exists for that scope If no session exists for the scope, exits with NO_SESSION and prompts for sessions new Is queue-aware when another prompt is already running for the same session On interrupt during an active turn, sends ACP session/cancel before force-kill fallback Prompt options: -s, --session <name> : use a named session within the same cwd --no-wait : enqueue and return immediately when session is already busy -f, --file <path> : read prompt text from file ( - means stdin) Exec (one-shot) acpx exec 'summarize this repo' acpx codex exec 'summarize this repo' acpx --model gpt-5.6-sol codex exec --config-option reasoning_effort=xhigh 'review this repo' Behavior: Runs a single prompt in a temporary ACP session Applies --model , then repeatable --config-option <key=value> selections, before prompting Fails before the prompt if the adapter rejects a requested config option Does not reuse or save persistent session state Compare (multi-agent one-shot) acpx compare pi openclaw codex 'summarize this checkout' acpx --format json compare codex claude --file prompt.md Behavior: Runs the same temporary-session prompt against each listed agent Runs agents serially in the requested workspace Reuses the global exec controls: cwd, timeout, permissions, --policy , auth, terminal, retries, model/system options, and output format --format text prints one summary table row per agent --format json or --json prints CompareRow[] --format quiet prints <agent>\t<status> per row Does not create saved sessions or separate compare transcript directories Cancel / Mode / Config / Model acpx codex cancel acpx codex set-mode auto acpx codex set model gpt-5.6-sol acpx codex set reasoning_effort max Behavior: cancel : sends cooperative session/cancel through queue-owner IPC. set-mode : calls ACP session/set_mode . set-mode mode ids are adapter-defined; unsupported values are rejected by the adapter (often Invalid params ). set : calls ACP session/set_config_option . Current codex-acp releases expose model and reasoning_effort as separate config options. --model <id> : Claude-compatible adapters may consume session creation metadata; other agents must advertise a model config option or legacy models metadata. set model <id> : uses session/set_config_option for advertised model config options and preserves session/set_model for explicitly advertised legacy models. Model switches can change or remove reasoning-effort controls. ACPX reconciles saved non-mode selections with the accepted response; select a supported effort again if needed. After reconnect, ACPX restores the saved model when advertised and replays saved config selections before prompting. A replay failure is reported instead of silently using defaults. set-mode / set route through queue-owner IPC when active, otherwise reconnect directly. Sessions acpx sessions acpx sessions list acpx sessions list --filter-cwd . acpx sessions list --cursor <cursor> acpx sessions list -- local acpx sessions new acpx sessions new --name backend acpx sessions ensure acpx sessions ensure --name backend acpx sessions close acpx sessions close backend acpx sessions show acpx sessions history -- limit 20 acpx sessions export backend --output backend-session.json acpx sessions import backend-session.json --name backend-restored acpx sessions prune --dry-run --older-than 7 acpx sessions prune --older-than 30 --include-history acpx status acpx codex sessions acpx codex sessions new --name backend acpx codex sessions ensure --name backend acpx codex sessions close backend acpx codex sessions show backend acpx codex sessions history backend -- limit 20 acpx codex sessions export backend --output backend-session.json acpx codex sessions import backend-session.json --name backend-restored acpx codex sessions prune --before 2026-04-01 --include-history acpx codex status Behavior: sessions and sessions list are equivalent sessions list uses ACP session/list when the agent advertises it; JSON includes agent SessionInfo , _meta , and nextCursor sessions list --filter-cwd <dir> applies the ACP cwd filter, and --cursor <cursor> requests a specific page sessions list --local reads saved acpx records instead new creates a fresh session for the current (agentCommand, cwd, optional name) scope new --name <name> targets a named session scope when new replaces an existing open session in that scope, the old one is soft-closed ensure returns the nearest matching active session for the scope, or creates one when none is open. Idempotent — safe to call before every prompt in scripts. close targets current cwd default session close <name> targets current cwd named session show [name] prints stored metadata for that scoped session history [name] prints stored turn history previews (default 20, use --limit ) export [name] --output <path> writes a portable JSON archive containing session state and event history import <archive> creates a fresh local record, reopens the copied session as idle, keeps the provider session id, and clears source-machine process metadata imported sessions must resume that provider session; if the destination agent cannot load it, prompts fail clearly instead of starting an empty conversation import --name <name> and --cwd <dir> override the destination scope; import fails if that scope already has an active session or another local record already uses the same provider session id prune deletes closed session records to reclaim disk space --dry-run previews what would be deleted without touching disk --older-than <days> and --before <date> filter by close time, falling back to last-used time when a record was never explicitly closed --include-history also removes per-session event stream files (otherwise only the JSON record is removed) Global options --agent <command> : raw ACP agent command (escape hatch) --cwd <dir> : working directory for session scope (default: current directory) --approve-all : auto-approve all permission requests --approve-reads : auto-approve reads/searches, prompt for writes (default mode) --deny-all : deny all permission requests --non-interactive-permissions <policy> : when prompting is unavailable, choose deny or fail --permission-policy <json-or-file> / --policy : per-tool ACP permission rules ( autoApprove , autoDeny , escalate , defaultAction ) --format <fmt> : output format ( text , json , quiet ) --json-strict : strict JSON mode; requires --format json and suppresses non-JSON stderr output --suppress-reads : suppress raw read-file contents while preserving the selected format --timeout <seconds> : max wait time (positive number) --ttl <seconds> : queue owner idle TTL before shutdown (default 300 , 0 disables TTL) --model <id> : request an agent model during session creation; non-Claude agents must advertise a model config option or legacy models metadata --system-prompt <text> : replace the agent system prompt. Forwarded to claude-agent-acp via ACP _meta.systemPrompt ; persisted in session_options.system_prompt so reuse keeps the override. Other agents ignore the field. --append-system-prompt <text> : append text to the agent system prompt. Forwarded to claude-agent-acp via ACP _meta.systemPrompt.append ; same persistence rules as --system-prompt . --allowed-tools <list> : comma-separated tool whitelist (use "" for no tools) --max-turns <count> : cap session turn count --prompt-retries <count> : retry failed prompt turns on transient errors (default 0 ) --no-fs : advertise both ACP filesystem capabilities as disabled so compatible agents use their native file operations --no-terminal : do not advertise the ACP terminal capability — useful for review-only or sandboxed agent invocations
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。