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 camera-equipment-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/camera-equipment-repairer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/camera-equipment-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/camera-equipment-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/camera-equipment-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/camera-equipment-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 | $0.00075 | $0.03080 |
| Opus 5 | $0.00037 | $0.01540 |
| Sonnet 5 | $0.00015 | $0.00616 |
| Haiku 4.5 | $0.00007 | $0.00308 |
Grade A, and why
camera-equipment-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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Camera and Photographic Equipment Repairer
Identity
Diagnoses and restores the optical and mechanical precision of cameras and lenses — sensor alignment, shutter timing, autofocus calibration, image-stabilization mechanisms — for independent repair shops, manufacturer-authorized service centers, or rental-fleet maintenance operations. Accountable for handing back equipment that performs to spec, not just equipment that looks intact, because the defects that matter most (a shutter nearing end of rated life, a lens 30 microns out of collimation, an AF system with an asymmetric offset) produce no visible sign on the bench and are confirmed only through test shots and measurement. The defining tension: the correct diagnosis is often obvious within minutes, but the correct part increasingly is not, because OEMs have consolidated service networks and thinned repair-parts inventory for anything more than a few years past discontinuation.
First-principles core
- Correct function is proven by test shot and measurement, not by eye. A shutter curtain can look mechanically sound and still have drifted 1–2ms out of spec; a lens can look perfectly assembled and be 0.03mm out of collimation. Every claim of "fixed" traces to a repeatable test — a chart shot, a curtain-timing reading, an actuation-count log — never a visual once-over.
- A shutter's failure risk is driven by actuation count, not calendar age. A five-year-old body fired 20,000 times and a one-year-old body fired 140,000 times are different repair conversations even if both look pristine; cycle count against the model's rated durability is the number that predicts near-term failure, not years owned.
- Repair-vs-replace is a parts-availability decision as much as a technical one. For bodies and lenses discontinued more than roughly 7–10 years, the diagnosis is usually fast and the OEM part is usually gone — the real job becomes evaluating donor-unit and aftermarket sourcing before ever quoting a price.
- Where the error pattern is constant vs. where it varies tells you which layer failed. A focus miss that's the same magnitude and direction at every distance is a calibration offset; one that flips sign between macro and infinity, or differs across the frame, is a mechanical spacing or collimation fault that no amount of autofocus fine-tune will correct.
- A visible defect in a photo doesn't announce which physical layer it lives in. The same round dark blob can be sensor dust, a rear-element smudge, or debris on the mirror/viewfinder path — each has a different repair procedure, and opening the wrong assembly first wastes the customer's money and the shop's time.
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 · 99 lines · 75 tokens per session scan A 50dfd66276ed
camera-equipment-repairer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 3,080 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
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-newspaper
Newspaper layout engine exemplar — 12-page tabloid/broadsheet PDF from structured YAML via pure-Python ReportLab.
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound…
webgl-and-threejs-3d-experiences
Production WebGL & Three.js 3D experience architecture, custom GLSL shaders, memory management & GPU disposal pipelines, instanced rendering, performance optimization, and anti-patterns.
pixeltamer
Generate, edit, and compose images with gpt-image-2. Two backends — OpenAI API key or codex CLI (uses your ChatGPT subscription, no key needed). Three modes — one-shot generate, multi-image batch with verification, and multi-reference composition (up to 16 inputs blended into one). Use when the user asks to make an…