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/nirholas/xactions/agent-troubleshootinggit clone --depth 1 https://github.com/nirholas/XActionsWhat 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 | $0.01374 |
| Opus 5 | $0.00000 | $0.00687 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
agent-troubleshooting 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Troubleshooting Guide
Common issues agents encounter when working on XActions and how to resolve them.
Tests
Tests fail with "Task not found: undefined"
Cause: TaskStore methods are async — calling store.create() without await returns a Promise, not a task object. Passing the Promise as a task ID fails.
Fix: Add await to all store.create(), store.get(), store.transition(), store.list() calls. Make test callbacks async.
Integration test worker crashes / times out
Cause: Usually an infinite pagination loop. scrapeUserList loops while (seen.size < limit). If the mock always returns the same response with a cursor and seen.size never reaches limit, it loops forever.
Fix: Use a call counter in the mock. Return a no-cursor response after the first call per endpoint:
let callCount = 0;
const fetchMock = vi.fn(async (url) => {
if (url.includes('Followers')) {
callCount++;
if (callCount > 1) return mockResponse({}); // no cursor → terminates
return mockResponse(graphqlBody(FOLLOWERS_RESPONSE));
}
});
x402-integration tests fail with 429 instead of 402
Cause: These tests require a running API server. Without the server, they hit a different endpoint.
Fix: Start the server first: npm run dev. Then run: npx vitest run tests/x402-integration.test.js.
Mutation mock returns wrong shape
Cause: For GraphQL queries, client.graphql() wraps the response as { data: json, cursor }. For mutations (mutation: true), it returns the raw JSON directly.
Fix: For mutation mocks, pass the full fixture with the data wrapper: mockResponse(TWEET_CREATE_RESPONSE), not mockResponse(graphqlBody(TWEET_CREATE_RESPONSE)).
Media upload test: "Cannot read properties of undefined (reading 'processing_info')"
Cause: MEDIA_FINALIZE_RESPONSE includes processing_info, which triggers a STATUS poll call. The mock has no response for this extra call, so it returns undefined.
Fix: Add a STATUS mock after FINALIZE: .mockResolvedValueOnce({}). The pollProcessingStatus function returns immediately when processing_info is absent.
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.
- 2d ago First seen · 143 lines · 0 tokens per session scan A 255041d82e8a
agent-troubleshooting is an agent published in the GitHub repository nirholas/XActions (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,374 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
AUDIT_MANIFEST
Total unimplemented-tagged scenarios: 76 Classified: 76.
ai-prompt-optimizer
LLM prompt engineering and optimization specialist.
harness-agent
Agent "harness-agent" from qidu/model_proxy_v3, covering installation, create an agent, run a turn, messages and history and session lifecycle.
langgraph
Trusted by companies shaping the future of agents-- including Klarna, Uber, J.P. Morgan, and more-- LangGraph is a low-level orchestration framework and runtime for building, managing, and deploying long-running, stateful agents.
proxy-as-provider-for-deepseek-harness
How to wire this proxy into deepseek-harness (dsh) as an LLM backend.
google-antigravity
The Google Antigravity SDK is a Python SDK for building AI agents powered by Antigravity and Gemini. It provides a secure, scalable, and stateful infrastructure layer that abstracts the agentic loop, letting you focus on what your agent does rather than how it runs.