troubleshoot-earl

troubleshoot-earl is a skill for Claude Code, Codex from mathematic-inc/earl. It costs 58 tokens per session (1,741 once invoked), scanned C, original, Apache-2.0.

A diagnostic and repair guide for Earl, a system that connects an AI agent to external services through templates and tools.

In plain words
What is it for?
Use it to run Earl's checks, validate templates, diagnose configuration or connectivity problems, and get instructions for secrets, browser authentication, restarts, or macOS permissions.
Why use it?
It helps locate common failures such as missing installation, template errors, authentication problems, unavailable tools, and blocked network requests. It also makes clear which fixes require action from a person.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it to run Earl's checks, validate templates, diagnose configuration or connectivity problems, and get instructions for secrets, browser authentication, restarts, or macOS permissions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mathematic-inc/earl/troubleshoot-earl
Install

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.

Any agent
npx skills add mathematic-inc/earl --skill troubleshoot-earl
Clone the repo
git clone --depth 1 https://github.com/mathematic-inc/earl

Made for: Claude Code, Codex.

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-earl

README.md
[![agentmods](https://agentmods.dev/badge/skills/mathematic-inc/earl/troubleshoot-earl/github.svg)](https://agentmods.dev/skills/mathematic-inc/earl/troubleshoot-earl)
Your own site
<a href="https://agentmods.dev/skills/mathematic-inc/earl/troubleshoot-earl"><img src="https://agentmods.dev/badge/skills/mathematic-inc/earl/troubleshoot-earl/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-earl

Your own site · 80×15
<a href="https://agentmods.dev/skills/mathematic-inc/earl/troubleshoot-earl"><img src="https://agentmods.dev/badge/skills/mathematic-inc/earl/troubleshoot-earl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,741 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00058 $0.01741
Opus 5 $0.00029 $0.00870
Sonnet 5 $0.00012 $0.00348
Haiku 4.5 $0.00006 $0.00174

Measured 9d ago against content hash ee0be39cc00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

troubleshoot-earl scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

# or: curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash

Makes network callslowCapability

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

# or: curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash
skills/development/troubleshoot-earl/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Troubleshoot Earl

Cold-start diagnostic for when Earl isn't working. Follow the steps in order — each step may reveal the root cause.

What Agents Can Fix

  • Earl not installed
  • HCL parse errors
  • Jinja render errors
  • Template not found
  • Wrong CLI flag order
  • MCP config missing or incorrect
  • SSRF blocks (suggest workaround)

What Requires Human Action

  • Secret values — agent prints checklist; human runs earl secrets set <key> manually
  • auth_code_pkce OAuth — agent provides command; human completes browser flow
  • Agent restart for MCP — agent notes this; continues with CLI mode
  • macOS keychain access dialog — agent warns; human clicks "Always Allow"

Step 1: Earl Doctor

earl doctor

If this fails with command not found: earl, Earl is not installed. Install it:

cargo install earl  # requires Rust toolchain + Node.js + pnpm
# or: curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash
# Windows: irm https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.ps1 | iex

If earl doctor reports other failures, address each one before continuing.


Step 2: Validate Templates

earl templates validate

Fix any errors found. Common errors and fixes:

Error message Cause Fix
HCL parse error / unexpected token Invalid HCL syntax Check structure, quotes, and braces
template root must be an object Missing top-level fields Add version = 1 and provider = "..."
template must define either 'commands' or 'command', not both Used both singular and plural form Use only command blocks
command X has empty title Missing title field Add title = "..." to the command block
undefined variable {{ args.x }} doesn't match a param name Check that param names match {{ args.x }} references
params = [{{ ... }}] Bare Jinja in HCL array Wrap in string: params = ["{{ ... }}"]

Read the full file on GitHub · 174 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. 9d ago First seen · 174 lines · 58 tokens per session scan C ee0be39cc00f

Subscribe to this mod's changes

troubleshoot-earl is a skill published in the GitHub repository mathematic-inc/earl (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,741 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories