DashClaw: Skill for Claude Code

.claude/skills/dashclaw-agent/troubleshoot/SKILL.md

troubleshoot is a skill for Claude Code from ucsandman/DashClaw. It costs 17 tokens per session (2,324 once invoked), scanned A, original, MIT.

A troubleshooting guide for DashClaw, including its errors, signals, and configuration settings.

In plain words
What is it for?
Use it to diagnose DashClaw API failures, authentication issues, policy blocks, demo or read-only modes, and organization setup problems.
Why use it?
It gives checks for common problems such as unauthorized requests, blocked actions, rate limits, and incorrect environment variables or permissions.

Skill for Claude Code

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

This is ucsandman/DashClaw's own configuration. It tells Claude Code how to work on DashClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DashClaw configures →

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.

Reuse

Borrowing it

Nothing to install: this file belongs to ucsandman/DashClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ucsandman/DashClaw/main/.claude/skills/dashclaw-agent/troubleshoot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

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/troubleshoot.svg)](https://agentmods.dev/skills/ucsandman/dashclaw/troubleshoot)
Your own site
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/troubleshoot"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/troubleshoot.svg" alt="Measured on agentmods" 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 2,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.02324
Opus 5 $0.00009 $0.01162
Sonnet 5 $0.00003 $0.00465
Haiku 4.5 $0.00002 $0.00232

Measured 7d ago against content hash 90ef16225a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/dashclaw-agent/troubleshoot/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 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 · 202 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. 7d ago First seen · 202 lines · 17 tokens per session scan A 90ef16225a98

Subscribe to this mod's changes

troubleshoot is a skill published in the GitHub repository ucsandman/DashClaw (297 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 2,324 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.