diagnose-check-engine-light

diagnose-check-engine-light is a skill for Claude Code from jeffreytse/grimoire-core. It costs 30 tokens per session (1,209 once invoked), scanned A, original, MIT.

A troubleshooting guide for an illuminated check-engine light, the vehicle warning that the engine or emissions system has detected a problem.

In plain words
What is it for?
Reading and assessing check-engine faults, deciding whether a vehicle is safe to drive, and choosing the next diagnostic or repair step.
Why use it?
It helps interpret OBD-II fault codes together with symptoms so the cause and urgency can be assessed before replacing parts or continuing to drive.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the grimoire-automotive plugin — 16 skills shipped together

Good fit Reading and assessing check-engine faults, deciding whether a vehicle is safe to drive, and choosing the next diagnostic or repair step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/diagnose-check-engine-light
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 jeffreytse/grimoire-core --skill diagnose-check-engine-light
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-automotive, the plugin that ships this one along with the rest of its 16 skills.

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 diagnose-check-engine-light

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/diagnose-check-engine-light/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/diagnose-check-engine-light)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/diagnose-check-engine-light"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/diagnose-check-engine-light/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 diagnose-check-engine-light

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/diagnose-check-engine-light"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/diagnose-check-engine-light.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00030 $0.01209
Opus 5 $0.00015 $0.00605
Sonnet 5 $0.00006 $0.00242
Haiku 4.5 $0.00003 $0.00121

Measured 10d ago against content hash 7b495fc47886, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

diagnose-check-engine-light 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 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.

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.

skills/automotive/troubleshooting/skills/diagnose-check-engine-light/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose Check Engine Light

Systematically identify the cause of an illuminated check engine light using OBD-II codes and symptom correlation to determine urgency and repair path.

Why This Is Best Practice

Adopted by: All US vehicles 1996+ (mandated by EPA OBD-II regulations), ASE-certified technicians, NHTSA emissions compliance programs, AAA diagnostic service network
Impact: OBD-II standardization (SAE J1979) enables diagnosis in minutes vs. hours of manual testing; correct code interpretation prevents $200–$1,500 in unnecessary part replacements; misdiagnosed CEL causes 35% of failed emissions tests (EPA data)
Why best: The SAE J1979 standard ensures any compliant scanner reads all 10,000+ standardized DTCs from any manufacturer; systematic correlation of code + symptoms + freeze-frame data eliminates guessing

Sources: SAE J1979 "E/E Diagnostic Test Modes" standard; NHTSA OBD-II enforcement; ASE "Automobile Test A6 (Electrical/Electronic Systems)" and "A8 (Engine Performance)" certification curricula

Steps

  1. Assess light behavior — Steady light: non-critical, engine likely still driveable; flashing/blinking light: active misfire causing catalytic converter damage — stop driving, tow to shop.

  2. Note symptoms — Before scanning, record: any rough idle, power loss, unusual smells, noises, fuel smell, smoke color; symptoms narrow diagnosis before the code is read.

  3. Connect OBD-II scanner — Plug scanner into DLC (Data Link Connector) under the dash, driver's side; turn key to ON (not start) or start engine per scanner instructions; for Bluetooth scanners, pair to app first.

  4. Read all stored DTCs — Retrieve all pending, current, and historical codes; a pending code (P0xxx with "pending" flag) has triggered once but not yet confirmed; record every code number.

  5. Decode each DTC — First digit: P=powertrain, B=body, C=chassis, U=network. Second digit: 0=generic SAE, 1=manufacturer-specific. Third digit: system (1=fuel/air, 2=injector, 3=ignition, 4=emission, 5=speed/idle, 6=output, 7/8=transmission). Decode using scanner database or NHTSA lookup.

Read the full file on GitHub · 60 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 · 60 lines · 30 tokens per session scan A 7b495fc47886

Subscribe to this mod's changes

diagnose-check-engine-light is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 30 tokens to every session and 1,209 once invoked, about $0.0002 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.