troubleshoot

troubleshoot is a skill for Claude Code from ucsandman/dashclaw-skills. It costs 17 tokens per session (2,169 once invoked), scanned A, a copy of troubleshoot, MIT.

A troubleshooting guide for DashClaw, a service that governs and monitors AI-agent actions. It maps common errors and unusual signals to checks for keys, permissions, configuration, policies, and service health.

In plain words
What is it for?
Use it to investigate HTTP errors, missing API keys, rotated keys, read-only access, demo mode, blocked actions, and other DashClaw setup issues.
Why use it?
It shortens the path from an error response to its likely cause, especially for authentication, permission, rate-limit, and policy-blocking problems.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/_run-with-env.mjs scripts/repair-stale-running-actions.mjs --dry-run --older-than-hours 1.

Good fit Use it to investigate HTTP errors, missing API keys, rotated keys, read-only access, demo mode, blocked actions, and other DashClaw setup issues.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ucsandman/dashclaw-skills
agentmods
npx agentmods add skills/ucsandman/dashclaw-skills/troubleshoot

Made for: Claude Code.

Wrote 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.

agentmods badge for troubleshoot

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/troubleshoot/github.svg)](https://agentmods.dev/skills/ucsandman/dashclaw-skills/troubleshoot)
Your own site
<a href="https://agentmods.dev/skills/ucsandman/dashclaw-skills/troubleshoot"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/troubleshoot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for troubleshoot

Your own site · 80×15
<a href="https://agentmods.dev/skills/ucsandman/dashclaw-skills/troubleshoot"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.02169
Opus 5 $0.00009 $0.01085
Sonnet 5 $0.00003 $0.00434
Haiku 4.5 $0.00002 $0.00217

Measured 10d ago against content hash 20287fd4b111, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

troubleshoot scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Test with curl:
Origin

This is a copy

89% identical to troubleshoot — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/troubleshoot/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Troubleshoot DashClaw

Systematic diagnostics for common DashClaw errors, signal anomalies, and configuration issues.

Error Code Diagnostics

401 Unauthorized

Symptom: API calls return 401.

Checklist:

  1. Verify x-api-key header is set (not Authorization: Bearer)
  2. Check DASHCLAW_API_KEY environment variable is set
  3. Confirm the key hasn't been rotated — API keys are shown once at creation
  4. Test with curl:
    curl -H "x-api-key: $DASHCLAW_API_KEY" $DASHCLAW_BASE_URL/api/health
    

Root cause: DashClaw uses x-api-key header, not Bearer tokens. The middleware does timing-safe comparison first, then falls back to hash lookup.

403 Forbidden

Symptom: API calls return 403.

Checklist:

  1. Demo mode? Demo mode blocks all write operations. Check DASHCLAW_MODE env var.
  2. Readonly key? Some keys are read-only. Check key permissions in dashboard.
  3. Guard blocking? If calling /api/guard and getting 403, a policy is blocking the action — this is working as intended.
  4. org_default trap? The org_default org blocks API access except onboarding routes. Create a real org first.

429 Rate Limited

Symptom: API calls return 429 Too Many Requests.

Defaults:

  • Production: 100 requests/minute per IP
  • Development: 1000 requests/minute per IP

Fixes:

  • Set DASHCLAW_DISABLE_RATE_LIMIT=true for local development
  • For production: use UPSTASH_REDIS_REST_URL for distributed rate limiting
  • Batch operations where possible

503 Server Misconfigured

Symptom: API calls return 503.

Checklist:

  1. Is DASHCLAW_API_KEY set? Missing key → 503 on protected routes
  2. Is DATABASE_URL valid? Check connection string
  3. Run health check: curl $DASHCLAW_BASE_URL/api/health
  4. Check the /setup page for readiness verification

Common Gotchas

Gotcha Explanation
Client-sent org headers stripped Middleware ALWAYS strips x-org-id, x-org-role, x-user-id from requests. Org context comes from the API key, never the client.
Two thread systems Context threads (ct_*) and message threads (mt_*) are separate systems. Don't mix them.
org_default blocks APIs Users in org_default are blocked from most endpoints. Create or join a real org first.
API key shown once Keys are displayed exactly once at creation. If lost, generate a new one.
2MB body size limit Request bodies larger than 2MB are rejected.
HTTPS required in production Non-HTTPS connections are rejected in production mode.
Canonical JSON for signatures Agent identity signatures require deterministic JSON key ordering.
Rate limiting is per-IP Not per-key or per-agent. Multiple agents on same IP share the limit.

Read the full file on GitHub · 200 lines

Changes

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.

  1. 10d ago First seen · 200 lines · 17 tokens per session scan A 20287fd4b111

Subscribe to this mod's changes

troubleshoot is a skill published in the GitHub repository ucsandman/dashclaw-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 2,169 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to troubleshoot, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens