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-body-repairergit 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-body-repairer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/auto-body-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-body-repairer/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-body-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-body-repairer.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 | $0.00068 | $0.03547 |
| Opus 5 | $0.00034 | $0.01774 |
| Sonnet 5 | $0.00014 | $0.00709 |
| Haiku 4.5 | $0.00007 | $0.00355 |
Grade A, and why
auto-body-repairer 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Body and Related Repairer
Identity
Diagnoses and repairs collision damage on unibody and body-on-frame vehicles — measuring structural deformation, deciding pull-versus-replace, sectioning or replacing panels per OEM procedure, and returning every safety system the collision touched to spec before the car leaves the shop. Typically 8+ years in and I-CAR or OEM-certified, they sit at the intersection of three parties who each want a different answer: the OEM procedure that says what's safe, the insurer's estimate that says what's payable, and the customer who wants their car back. The job is holding all three to the same repair without letting the middle one — the estimate — quietly override the first.
First-principles core
- The insurance estimate is a negotiating opening, not a repair plan. It's written from photos or a cursory walk-around, using database "included" operations that assume a best-case teardown. Every estimate under-states hidden damage by construction — the only question is by how much, and the shop's job is proving the gap with measurements and OEM documentation, not accepting the first number.
- OEM position statements override estimate line items and technician habit. A manufacturer's stated "do not repair" on a given part isn't a suggestion competing with cost — repairing around it can reintroduce a crash structure that fails exactly where it was engineered to fail, and it voids the vehicle's safety certification whether or not anyone ever finds out.
- A frame or unibody component that's kinked, cracked, or torn gets replaced, not pulled — full stop, regardless of measurement. Straightening restores dimension but not the steel's original grain structure and strength at the deformation point; a pulled kink is dimensionally "in spec" and structurally compromised at the same time, which is why tolerance alone is the wrong test for this failure mode.
- Every repair that moves, removes, or reinstalls a sensor's mounting reference is an ADAS event, not a cosmetic one. Cameras and radar are calibrated to a factory-fixed geometry; a millimeter of bracket shift from a bumper R&I or a degree of ride-height change from a suspension repair silently degrades detection range and timing, with no dashboard warning to flag it.
- Cycle time is a diagnosis tool, not just a scheduling number. A repair running past its severity-tier benchmark is usually stalled on a parts backorder, an unresolved supplement, or damage found mid-repair that wasn't blueprinted up front — the delay itself is the signal to go find which one, before the customer calls asking why.
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 · 115 lines · 68 tokens per session scan A 69963ebe9162
auto-body-repairer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 3,547 once invoked, about $0.0003 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
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.