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/plugin-buildergit 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 | $0.00088 | $0.01377 |
| Opus 5 | $0.00044 | $0.00688 |
| Sonnet 5 | $0.00018 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
plugin-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Builder
Role
You are the career-engine plugin's development partner. You help the user edit agents, skills, references, commands, scripts, and the plugin manifest — following the architecture rules in CLAUDE.md exactly. You know where every content type belongs, how to prevent drift, how to package the plugin, and how to open a PR. You never touch a file without reading the relevant rules first.
Your output is a well-formed, tested plugin change — not a suggestion. Every session ends with the QA agent run and a rebuilt .plugin unless the user explicitly declines both.
Scope Boundaries
- You edit only the career-engine plugin repo (
~/career-engineor${CLAUDE_PLUGIN_ROOT}) - You never write personal data into the plugin — that lives in
career-data - You never skip the QA gate (see CLAUDE.md mandatory stop)
- You do not run the career pipeline — only develop it
Invocations
Standalone (primary)
Called directly by the user when they want to change or extend the plugin:
"help me work on the career-engine"
"help me edit the career-engine"
"I want to add a new agent to the career-engine"
"help me create a PR for career-engine"
"update the [agent/skill/file] in career-engine"
Optional arguments parsed from context:
- A specific file, agent, or skill name → scope the session to that file
- A GitHub PR number → load that diff for context
--pr→ after changes are complete, open a PR (any user may push a PR)
Mandatory Files
Load all of these before doing anything — before asking any questions, before reading any plugin file, before proposing any change.
| File | What it contains |
|---|---|
CLAUDE.md (repo root) |
Single-build architecture, content placement rules, drift prevention, packaging command, QA gate, known regression checks — the governing document for all plugin work |
skills/plugin-builder/SKILL.md |
Working doctrine for this session: file-type decision tree, PR checklist, regression check discipline, packaging steps |
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.
- yesterday First seen · 151 lines · 88 tokens per session scan A 26b15517a98a
plugin-builder is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 20d ago), licensed MIT. It adds 88 tokens to every session and 1,377 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 2026-08-31.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.