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 humanerd-drew/opencode-drewgent --skill goose-acp-integrationgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/goose-acp-integration)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/goose-acp-integration"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/goose-acp-integration.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 | $0.00034 | $0.01048 |
| Opus 5 | $0.00017 | $0.00524 |
| Sonnet 5 | $0.00007 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
goose-acp-integration 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goose ACP Integration for {{AGENT_NAME}}
What is ACP
Agent Client Protocol (ACP) is a JSON-RPC-based standard for communicating with coding agents (GitHub: agentclientprotocol).
goose uses ACP to connect to agents like Claude Code as provider (subprocess communication over stdio):
goose → claude-agent-acp (NPM) → Claude Code CLI → Anthropic API
Key ACP providers in goose:
claude_acp.rs— Claude Code via@agentclientprotocol/claude-agent-acpcodex_acp.rs— OpenAI Codexcopilot_acp.rs— GitHub Copilot
Key Protocol Types (agent_client_protocol schema)
InitializeRequest/Response // handshake
NewSessionRequest/Response // create session
PromptRequest/Response // send messages
SessionNotification // async events (tool calls, permissions, completion)
- ToolCallStart { id, name, kind, raw_input }
- ToolCallComplete { id, raw_output, content[], is_error }
- PermissionRequest { request: RequestPermissionRequest }
- Complete(StopReason, Option<Usage>)
ToolCallContent / ToolCallStatus
RequestPermissionResponse
How goose connects to Claude Code
// crates/goose/src/providers/claude_acp.rs
let config = AcpProviderConfig {
command: resolved_command, // path to claude-agent-acp
args: vec![],
env: vec![],
work_dir: current_dir,
mcp_servers: extension_configs_to_mcp_servers(&extensions), // {{AGENT_NAME}} tools as MCP
session_mode_id: Some(mode_mapping[&goose_mode].clone()),
// mode_mapping:
// Auto → bypassPermissions (fully autonomous)
// Approve → default (ask before risky)
// SmartApprove → acceptEdits (auto-accept edits)
// Chat → plan (plan only)
};
AcpProvider::connect(name, model, goose_mode, config).await
AcpProvider (crates/goose/src/acp/provider.rs):
- Spawns subprocess (stdio JSON-RPC)
- Sends
initializethennewSession - Streams
SessionNotificationback (tool calls, permissions) - Sends tool results via
CallToolResult
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 · 108 lines · 34 tokens per session scan A aea716e624bb
goose-acp-integration is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,048 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 2026-08-31.
Other skills, from other repositories
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
mcp-protocol-suite
Model Context Protocol (MCP) tool integration for connecting external MCP servers, enterprise tools, and APIs.
mcp-builder
Guide for creating advanced-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
peer-review
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…