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 agents/openclaw/acpx/claudegit clone --depth 1 https://github.com/openclaw/acpxWhat 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 | $0.00000 | $0.00217 |
| Opus 5 | $0.00000 | $0.00109 |
| Sonnet 5 | $0.00000 | $0.00043 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
Claude 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 yesterday.
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.
What it actually says
Claude
- Built-in name:
claude - Default command:
npx -y @agentclientprotocol/claude-agent-acp - Upstream: https://github.com/agentclientprotocol/claude-agent-acp
- ACPX pins the built-in package range so fresh installs pick up Claude model and ACP adapter fixes without depending on a global adapter binary.
- Model switches can change the available effort controls. ACPX updates existing saved effort selections from the accepted response and removes selections whose controls disappear.
- Saved model and config selections are restored after reconnect, without replacing the conversation.
Settings isolation
Built-in acpx claude sessions load Claude project and local settings, but not
user settings. This prevents globally enabled channel and daemon plugins from
claiming singleton external resources in an ACP-spawned session.
Set ACPX_CLAUDE_INCLUDE_USER_SETTINGS=1 only when the spawned session needs
the user's global Claude settings and no such plugin conflict exists. Ambient
credentials and other environment variables are still inherited normally.
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.
- yesterday First seen · 19 lines · 0 tokens per session scan A daa68dffbac3
Claude is an agent published in the GitHub repository openclaw/acpx (3,194 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 217 tokens. 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 agents, from other repositories
code-quality-reviewer
Use this agent when you want a comprehensive review of code quality, readability, structure, and maintainability. This agent focuses on how well-written and organized code is — not on bugs, logic errors, or functional correctness. It examines file length, function complexity, naming conventions, code organization…
refactor-analyst
Use this agent when you need a thorough code quality analysis and refactoring recommendations for specific files, directories, or an entire branch. This agent reads code deeply, questions every pattern, checks for modern best practices, and produces a detailed report — without making any changes.\n\nExamples:\n\n…
typescript-type-reviewer
Use this agent when you need a thorough review of TypeScript type definitions, type usage patterns, and type architecture in recently written or modified code. This includes checking for type duplicates, unnecessary custom type copies that should be imported from libraries, improper type assertions, overly broad…
perf-deep-audit
Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially for large renders, long chat histories, streaming updates, memory leaks, IPC bottleneck analysis, or general app sluggishness investigations. This agent reviews and diagnoses only; it does not edit…
docs-researcher
Use this agent when the user needs information from project documentation files, SDK docs, protocol specs, or any @docs prefixed directories. This includes questions about API usage, SDK methods, protocol details, configuration options, type definitions, or architectural decisions documented in the codebase. The agent…
clean-code-refactor
Use this agent when you need to refactor existing code, rewrite a module for better maintainability, decompose a large file into focused sub-modules, eliminate duplication, improve type safety, optimize performance, or generally elevate code quality. This agent goes beyond the minimum ask — it proactively identifies…