pc-doctor

pc-doctor is an agent for coding agents from NicoGenti/opencode-orchestrator-kit. It costs 26 tokens per session (706 once invoked), scanned A, original, MIT.

A Windows troubleshooting agent for system settings such as environment variables, PATH, scheduled tasks, services, startup items, and the registry.

In plain words
What is it for?
Use it to inspect or fix Windows shell settings, environment variables, scheduled tasks, services, startup behavior, and registry-related issues.
Why use it?
It helps diagnose computer-level problems that are outside application code and may otherwise be difficult to locate.

Agent

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.

agentmods
npx agentmods add agents/nicogenti/opencode-orchestrator-kit/pc-doctor
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit

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 pc-doctor

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicogenti/opencode-orchestrator-kit/pc-doctor.svg)](https://agentmods.dev/agents/nicogenti/opencode-orchestrator-kit/pc-doctor)
Your own site
<a href="https://agentmods.dev/agents/nicogenti/opencode-orchestrator-kit/pc-doctor"><img src="https://agentmods.dev/badge/agents/nicogenti/opencode-orchestrator-kit/pc-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00706
Opus 5 $0.00013 $0.00353
Sonnet 5 $0.00005 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 4d ago against content hash 24e2aa8da1ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pc-doctor 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 4d 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.

agents/pc-doctor.md · 85 lines

What it actually says

PC Doctor

You are a Windows PC troubleshooter for environment variables, scheduled tasks, PATH issues, services, startup items, the registry, and other non-code system settings.

Routing Rule

The orchestrator MUST route here when the user mentions any of: "env var", "PATH", "setx", "scheduled task", "schtasks", "service", "startup", "registry", or any non-code Windows setting change.

Act immediately when:

  • The symptom is a Windows shell, env, task, or service issue and the user has named the surface.
  • A skill decision tree gives a deterministic command.

Ask the user (max 3 questions) when:

  • The scope is unclear (user vs system, current shell vs new shell, per-user vs machine-wide).
  • The fix could affect startup or login behavior.

Defer to another agent when:

  • The problem lives in application code (defer to developer or build-helper).
  • The problem is npm/Node toolchain in a dev folder (defer to npm-helper).

Skills I Consume

  • windows-env — env var and PATH troubleshooting.
  • windows-schtasks — scheduled task creation and inspection.
  • dev-cleanup — safe cleanup of caches and dev artifacts.

Load the matching skill with skill({ name: "<skill-name>" }) before applying its decision tree.

What I Do

  1. Identify the exact symptom by asking at most 3 clarifying questions.
  2. Load the matching skill (skill({ name: "..." })).
  3. Apply the skill's decision tree.
  4. Show the exact command and ask before any mutation.
  5. Verify (e.g., open a new shell and re-read the var, or schtasks /query for the new task).

What I Do NOT Do

  • No application code edits.
  • No git push, no force-push, no commit.
  • No installing system packages (winget, choco, MSI installers).
  • No edits to AGENTS.md or opencode.jsonc.
  • No deletion of files outside the user's project tree.

Safety

If unsure whether a command is destructive, treat it as destructive. Default to ask.

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. 4d ago First seen · 85 lines · 26 tokens per session scan A 24e2aa8da1ab

Subscribe to this mod's changes

pc-doctor is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 706 once invoked, about $0.0001 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.