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/humanerd-drew/opencode-drewgent/acp-thinking-spinnernpx skills add humanerd-drew/opencode-drewgent --skill acp-thinking-spinnergit 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/acp-thinking-spinner)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/acp-thinking-spinner"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/acp-thinking-spinner.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 | $0.00082 | $0.01835 |
| Opus 5 | $0.00041 | $0.00918 |
| Sonnet 5 | $0.00016 | $0.00367 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
acp-thinking-spinner 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 5d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACP Thinking Spinner — Tool-Card Pattern
When an ACP server ({{AGENT_NAME}}'s acp_adapter/, Hermes, or any Agent Client Protocol implementation) needs to show a working indicator during the LLM API call phase, the standard approach is to synthesize a virtual tool call with kind="think". This places a "Thinking..." card in the client's tool-call stack — the same place real tool calls appear, which is the most reliable UI surface.
Why this pattern (root-cause: ACP spec gap)
ACP has no dedicated channel for "agent is generating a response." It only has:
| Channel | Where it renders | Problem |
|---|---|---|
update_agent_thought_text |
Client's "Thinking" area | Most clients render this as static text — JetBrains got stuck on "Thinking" with rawInput updates, others don't blink. Unreliable for "is it stuck?" UX. |
update_agent_message_text |
Answer streaming area | Only fires once streaming actually starts; doesn't cover the 0-30s gap before first delta. |
ToolCallStart / ToolCallUpdate |
Tool-call stack (openCode-style) | The most reliable UI surface — clients render an animated spinner here for any tool call. Synthesizing a virtual think-kind call works. |
| Status bar | Client-specific | Not standardized in ACP — see agentclientprotocol.com/rfds/session-usage (RFD, not yet spec). Cannot trigger from the server. |
Conclusion: For a "is it stuck or working?" signal in ACP, the only reliable channel is the tool-call stack. Use a virtual kind="think" card.
State machine
start → ToolCallStart(kind="think", title="Thinking...")
heartbeat → ToolCallUpdate(status="in_progress", elapsed text) # at 30s, 60s, ...
complete → ToolCallUpdate(status="completed")
Hook sites in the LLM call lifecycle:
- Before
_interruptible_api_call()/_interruptible_streaming_api_call()→start - First streamed delta (
on_first_deltacallback) →complete - Long-running timer (e.g.
threading.Timer(30.0, ...)) →heartbeat; cancel on complete
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.
- 5d ago First seen · 136 lines · 82 tokens per session scan A 42b5ab96c2b5
acp-thinking-spinner is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,835 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…