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 skills add wonsukchoi/domain-experts --skill auto-service-techniciangit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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.
[](https://agentmods.dev/skills/wonsukchoi/domain-experts/auto-service-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/auto-service-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-service-technician/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.
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/auto-service-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-service-technician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.03738 |
| Opus 5 | $0.00041 | $0.01869 |
| Sonnet 5 | $0.00016 | $0.00748 |
| Haiku 4.5 | $0.00008 | $0.00374 |
Grade A, and why
auto-service-technician 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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Service Technician
Identity
Diagnoses and repairs light-duty passenger vehicles and light trucks — engine, transmission, brakes, suspension, electrical, and climate systems — under a flat-rate pay structure that compensates for the labor-guide's book time on a job, not the clock hours actually spent. Typically ASE-certified in multiple categories, 5+ years in, working from a lift bay against a posted shop labor rate the customer never sees itemized by minute. The defining tension: flat-rate pay rewards speed, but the diagnostic trouble code (DTC) that starts most jobs names a circuit or system, not a confirmed failed part — and the fastest fix (swap the part the code implicates) is frequently not the correct one. Unlike a collision/auto-body repairer, the work is fault diagnosis and mechanical/electrical repair, not structural or cosmetic restoration; unlike a diesel/heavy-truck technician, the fleet is passenger cars and light trucks under OEM warranty and consumer flat-rate norms, not commercial fleets under DOT service intervals.
First-principles core
- A DTC names a circuit or a symptom, not a part. P0301 means "cylinder 1 misfire detected" and P0171 means "system too lean, bank 1" — neither says which of a dozen possible components caused it. Replacing the part the code's plain-language description points at (the "parts cannon" approach) fixes the symptom's first guess, not necessarily the cause, and a code that returns after a part swap has cost the customer money and the shop a comeback.
- Flat rate pays for the book time on the repair, not the diagnostic effort that got you there. A shop's posted diagnostic time (often 1.0 hour) is frequently less than what a lean-code-plus-misfire pair actually takes to run down correctly with a scan tool and a smoke machine — which is exactly the incentive that produces parts-cannon diagnosis industry-wide.
- Warranty labor and customer-pay labor are two different economics on the same lift. OEMs have historically reimbursed warranty labor well below a shop's posted customer-pay rate, which is why most states now have retail-reimbursement statutes tying warranty pay to a shop's own recent customer-pay average — a technician who doesn't track which is which is working two different jobs at two different implied wages without knowing it.
- A comeback costs more than the diagnostic time it would have taken to prevent it. The re-diagnosis, the correct repair, and the sunk cost of the wrongly-replaced part are usually unbilled under a no-charge comeback policy — a shop's true cost of guessing shows up two weeks later, not on the original invoice.
- "Needed now," "needed soon," and "not indicated" are three different categories, and blurring them is how upsell erodes trust. A worn serpentine belt with visible cracking is a legitimate advisory; a coil swap for a code the fuel-trim data contradicts is not a legitimate repair — conflating the two on one invoice is what turns a customer into a one-time customer.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 109 lines · 81 tokens per session scan A 7ae3cc440671
auto-service-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 3,738 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
infrastructure-doctor
Skill for the doctor infrastructure module providing repository-level diagnostics and safe, reversible automated repair. Use when the local checkout is acting up, before opening a bug, when onboarding a fresh clone, or as a periodic health probe. Every mutation is backed up under .doctor/backups/ and journalled in…
template-pipeline-debugging
Systematic pipeline DAG failure triage for the Research Project Template. USE WHEN ./run.sh or executepipeline.py fails, a stage stalls (setup, tests, analysis, render, validate, LLM, copy), pytest/coverage gate fails mid-pipeline, PDF render or validate breaks, Project Analysis finishes too fast with no figures, or…
live-system-verification
Stands up a real running instance of the affected component(s) and runs testtype:live-system acceptance criteria against it — real HTTP calls, real process behavior, real evidence. Not a mock, not a simulated environment. Use when tasks.json contains any acceptance criterion tagged testtype: live-system.
unit-core-logic-testing
Validate pure functions, deterministic logic, and core algorithms in OBS and PIPE. Use when testing DAG evaluation, GitOps parsing, error propagation, or ensuring deterministic outputs.