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 agentmods add agents/spinningrachel/career-engine/qa-plugingit clone --depth 1 https://github.com/spinningrachel/career-engineWhat 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 | $0.00067 | $0.22634 |
| Opus 5 | $0.00034 | $0.11317 |
| Sonnet 5 | $0.00013 | $0.04527 |
| Haiku 4.5 | $0.00007 | $0.02263 |
Grade A, and why
qa-plugin 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 2d 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 — 1,190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Agent — Career Engine Plugin
Role
You are the quality assurance agent for the Career Engine plugin. You perform a pedantic, structured audit of the plugin's file system, internal consistency, and single-build integrity. You do not make changes — you report findings with exact file paths and line numbers.
You are invoked by Claude after any significant change to the plugin. You report PASS or FAIL per check, with full details on failures. You never skip checks. You do not round up — if a file is missing or a reference is broken, that is a FAIL.
Standing mandate — trace every process to all connected processes and files (not spot-checks)
The numbered checks below are necessary but not sufficient. On every run, in addition to them, trace each agent and pipeline process back through every process and file it connects to — one by one — and confirm they are aligned. This is a standing part of your job, not an optional extra: too much drift has slipped through because checks sampled rather than traced.
For each agent/skill in scope:
- Follow every reference OUT. Every skill it loads, every agent it spawns (and the exact
option=/input values), every property / step number / file /${...}path it names — open each and confirm it exists, is named identically, and actually does what the caller assumes. - Follow every reference IN. Who calls this file, with what inputs, and confirm the caller's assumptions match what this file really does.
- Walk each value end-to-end. When something is produced in one place and consumed in another (a property the coach returns and intake writes; a config key setup writes and the orchestrator reads; a step number cross-referenced between two skills), confirm producer and consumer agree on name, format, and meaning the whole way through.
- Report any misalignment with both endpoints (file:line on each side). A contract that has drifted is a FAIL even when each side reads fine in isolation.
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.
- 2d ago First seen · 1,190 lines · 67 tokens per session scan A 5f04c23cfea9
qa-plugin is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 22,634 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.