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 agentmods add skills/carlos-algms/agentic.nvim/agentic-acp-protocol-flownpx skills add carlos-algms/agentic.nvim --skill agentic-acp-protocol-flowgit clone --depth 1 https://github.com/carlos-algms/agentic.nvimWrote 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/carlos-algms/agentic.nvim/agentic-acp-protocol-flow)<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>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 | $0.00046 | $0.00542 |
| Opus 5 | $0.00023 | $0.00271 |
| Sonnet 5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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.
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
ACPClientinacp_client.lua. - There are no per-provider adapter files. See ADR 0005.
- Add a provider with a
config_default.luaentry underacp_providersunless the provider deviates from ACP in a new way. - Provider quirks live in protected
ACPClientmethods, 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/updaterouting, 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.
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.
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.
- 6d ago First seen · 67 lines · 46 tokens per session scan A 0871172a9b6e
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.
Other skills, from other repositories
add
Categorize new Neovim plugins and insert them into the correct markdown category files.
write-teach-commit
Draft teach: commit messages for .github/workflows/improve-add-skill.yml. Use when preparing or reviewing a correction commit that should trigger the Improve Add Skill workflow from $add categorization feedback, including moved plugin entries, removed or excluded plugins, changed .reason.md categories, or…
improve-add-skill
Improve the repo-local add skill from reviewed Neovim plugin categorization corrections. Use when a correction commit, PR review result, diff, or artifact such as a teach: commit shows that $add placed, excluded, or reasoned about plugins incorrectly and the reusable lesson should be folded back into…
git-branch-commit-pr
Automates the workflow of creating a feature branch, committing changes, and opening a PR. Use this when asked to create a branch, make changes, commit, and open a pull request for Lua code improvements or fixes.
bro
Restate the last message in plain human language, with no jargon.
commit
Create conventional commits. Use when: committing staged changes. Triggers on: '/commit', 'conventional commit'.