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 skills/spinningrachel/career-engine/plugin-buildernpx skills add spinningrachel/career-engine --skill 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 | $0.00052 | $0.01980 |
| Opus 5 | $0.00026 | $0.00990 |
| Sonnet 5 | $0.00010 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
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 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Builder — Working Doctrine
This skill is the craft layer for plugin-builder sessions. The governing rules live in CLAUDE.md — read that first. This skill gives you the decision trees, checklists, and conventions you need to apply those rules without re-deriving them every time.
The Three Questions Before Every Change
Before touching any file, answer these three questions:
- What content type is this? (See content-type decision tree below.)
- Which file owns this content type? (See content placement rules in CLAUDE.md.)
- Is it personal data? If yes, it belongs in
career-data, never the plugin.
If you cannot answer all three confidently, ask the user before writing.
Content-Type Decision Tree
Is it a rule about what to write, how to write it, or a writing philosophy?
→ skill file (skills/<name>/SKILL.md)
Is it a step-by-step procedure, a routing decision, or an output format spec?
→ agent file (agents/<name>.md)
Is it the user's personal data — role facts, voice profile, sent letters, .dotx?
→ career-data skill (never the plugin)
Is it a blank template with {{...}} placeholders for the user to fill at setup?
→ references/ in the plugin
Is it a slash command that invokes a skill or agent?
→ commands/ in the plugin
When something could fit two categories, the tie-break is: does it apply every time this task runs? If yes → skill. If it varies by session input → agent.
Before Writing a New Agent
A new agent needs all of the following in the same session. Do not close the session until every item is done:
- Agent file at
agents/<name>.mdwith frontmatter (name,description,tools) - Skill directory at
skills/<name>/SKILL.mdwith frontmatter (name,description,allowed-tools) - If it introduces a new pipeline: a row in the Pipeline Registry in
CLAUDE.mdand in thecareer-engineentry skill - If it reads reference files: a loading table in the agent file pointing at the right files
- If it writes new reference files: those files added to
references/REFERENCES.mdand wired into every consuming agent - QA run and
.pluginrebuild
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 · 164 lines · 52 tokens per session scan A ef5a00ff82a2
plugin-builder is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 20d ago), licensed MIT. It adds 52 tokens to every session and 1,980 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 skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…