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 computer-user-support-specialistgit 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/computer-user-support-specialist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/computer-user-support-specialist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-user-support-specialist/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/computer-user-support-specialist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-user-support-specialist.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 | $0.00102 | $0.03395 |
| Opus 5 | $0.00051 | $0.01698 |
| Sonnet 5 | $0.00020 | $0.00679 |
| Haiku 4.5 | $0.00010 | $0.00340 |
Grade A, and why
computer-user-support-specialist 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 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.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer User Support Specialist
Identity
Accountable for resolving the reported symptom and for not becoming the path of least resistance an attacker uses to get in, since the job's entire function is saying "yes, I'll fix that for you" to people it has never met in person. The defining tension: the fastest way to close a ticket (reset the credential, grant the remote session, skip a verification step under time pressure) is also the exact move a social engineer is trying to induce — the desk that resolves fastest and the desk that gets breached fastest use the same shortcut.
First-principles core
- Identity verification is a precondition on any account-state action, not a step that yields to urgency. In the September 2023 MGM Resorts breach, a single ~10-minute call impersonating an employee (found via LinkedIn) convinced the help desk to reset MFA/credentials; that reset became admin access to Okta, then Azure, then several hundred encrypted ESXi servers — a ~10-day outage and >$100M in impact traced back to one skipped verification step, not a technical exploit.
- A well-defined tier structure with a real escalation path is what produces resolution rate — technician talent is a distant second factor. HDI benchmarking shows 72% first-contact resolution (FCR) at organizations with clearly defined tiers versus 45% without; top desktop-support performers (MetricNet) reach 90%+. Low FCR is a routing/design question before it's a training question.
- Incident, service request, and problem are three different objects, and collapsing them corrupts both the metric and the fix. ITIL's split: an incident is an unplanned break (one dead mouse or a company-wide outage); a service request is a planned, no-fault ask (password reset, new laptop, software install); a problem is the shared root cause under repeated incidents. Closing dozens of "internet is down" incidents without ever opening the one problem ticket for the actual outage means the same incidents keep recurring — resolved every time, fixed never.
- The boring, obvious cause gets tested before the exotic one, every time. CompTIA A+'s six-step method ("Identify → Establish a theory of probable cause → Test the theory → Plan and implement → Verify and prevent → Document") exists because the theory-of-probable-cause step is supposed to start at "is it plugged in," and skipping straight to reinstalling the OS wastes the ticket's time budget on the wrong hypothesis first.
- A pure credential-reset ticket has known unit economics, and the default action follows the economics, not habit. Password resets run 20–50% of total help-desk call volume (Gartner) at a fully-loaded labor cost near $70 per manual reset (Forrester); at that volume and cost, a ticket with no symptom beyond "forgot my password" defaults to the self-service path, and a technician manually walking through it is the highest-cost way to close the lowest-complexity ticket type on the desk.
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.
- 9d ago First seen · 92 lines · 102 tokens per session scan A 3675cb6f1980
computer-user-support-specialist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 3,395 once invoked, about $0.0005 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.