agentic-acp-protocol-flow

agentic-acp-protocol-flow is a skill for Claude Code, Codex from carlos-algms/agentic.nvim. It costs 46 tokens per session (542 once invoked), scanned A, original, MIT.

Guidance for the Agent Client Protocol flow in agentic.nvim. ACP is a protocol that lets the plugin communicate with external coding-agent programs through subprocesses and route their messages, tools, permissions, and sessions.

In plain words
What is it for?
Use it when editing ACP clients or transport, provider switching, tool-call parsing, permission requests, reconnect behavior, or subprocess lifecycle handling.
Why use it?
It helps changes fit the existing communication pipeline and prevents provider-specific behavior from being placed in the wrong part of the system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions OpenCode.

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/carlos-algms/agentic.nvim/agentic-acp-protocol-flow
Any agent
npx skills add carlos-algms/agentic.nvim --skill agentic-acp-protocol-flow
Clone the repo
git clone --depth 1 https://github.com/carlos-algms/agentic.nvim

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 agentic-acp-protocol-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/carlos-algms/agentic.nvim/agentic-acp-protocol-flow.svg)](https://agentmods.dev/skills/carlos-algms/agentic.nvim/agentic-acp-protocol-flow)
Your own site
<a href="https://agentmods.dev/skills/carlos-algms/agentic.nvim/agentic-acp-protocol-flow"><img src="https://agentmods.dev/badge/skills/carlos-algms/agentic.nvim/agentic-acp-protocol-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 542 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 $0.00046 $0.00542
Opus 5 $0.00023 $0.00271
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 6d ago against content hash 0871172a9b6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agentic-acp-protocol-flow 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 6d 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.

.agents/skills/agentic-acp-protocol-flow/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic ACP Protocol Flow

Use this skill for ACP runtime behavior. For schema facts, also load agentic-acp-docs-and-schema.

Provider model

  • External ACP CLI tools are spawned as subprocesses.
  • The plugin does not install providers.
  • All providers use the generic ACPClient in acp_client.lua.
  • There are no per-provider adapter files. See ADR 0005.
  • Add a provider with a config_default.lua entry under acp_providers unless the provider deviates from ACP in a new way.
  • Provider quirks live in protected ACPClient methods, not adapter files.

Pipeline

provider subprocess
-> ACPTransport
-> ACPClient
-> SessionManager subscriber
-> MessageWriter / PermissionManager / TodoList / ChatHistory

Load references by edit target

  • references/client-lifecycle.md: ACPClient.state, ready listeners, sync vs async dispatch, reconnect, pending callback draining.
  • references/transport-framing.md: stdio line framing, partial chunks, subprocess process-group termination.
  • references/tool-calls-permissions.md: session/update routing, tool-call lifecycle, permission request normalization, provider quirks.
  • references/provider-switch-options.md: provider switch replay, modes/models, thought level, config options.

Protected methods

Current extension points:

Method Behavior
__handle_tool_call Builds ToolCallBlock, notifies subscriber
__build_tool_call_message Parses ACP fields and quirk fallbacks
__handle_tool_call_update Builds partial, notifies subscriber
__handle_request_permission Sends permission result to provider
__handle_session_update Routes by sessionUpdate type

Only subclass or extend these when a real provider deviation requires it.

Provider quirks

Handle protocol deviations inline in __build_tool_call_message.

Read the full file on GitHub · 67 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 67 lines · 46 tokens per session scan A 0871172a9b6e

Subscribe to this mod's changes

agentic-acp-protocol-flow is a skill published in the GitHub repository carlos-algms/agentic.nvim (611 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 542 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.