Borrowing it
Nothing to install: this file belongs to spinningrachel/career-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spinningrachel/career-engine/main/CLAUDE.mdgit clone --depth 1 https://github.com/spinningrachel/career-engineWrote 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/instructions/spinningrachel/career-engine/claude-md)<a href="https://agentmods.dev/instructions/spinningrachel/career-engine/claude-md"><img src="https://agentmods.dev/badge/instructions/spinningrachel/career-engine/claude-md.svg" alt="Measured on agentmods" 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 | $0.42217 | $0.42217 |
| Opus 5 | $0.21108 | $0.21108 |
| Sonnet 5 | $0.08443 | $0.08443 |
| Haiku 4.5 | $0.04222 | $0.04222 |
Grade B, and why
career-engine CLAUDE.md scanned grade B with 1 finding 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 7d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
**Placeholder resolution.** The plugin's instruction files keep `{{...}}` placeholders literally — they are NOT substituted at install, because substituting them would personalize the shared build. Agents resolve them at How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Career Engine Plugin
Working instructions for Claude when editing, extending, or maintaining this plugin.
⛔ MANDATORY STOP — READ BEFORE DOING ANYTHING ELSE
You are not done with any plugin edit session until the QA agent has run and passed. No exceptions.
This means: after completing any set of changes — no matter how small — you MUST invoke the QA agent (agents/qa-plugin.md) before telling the user the work is complete. This is not optional and cannot be skipped because the changes "seem clean" or because you "already checked manually." Manual checking is how drift accumulates silently.
The plugin is a single build. There is no second personalized copy to keep in sync: the user's personal data lives entirely in the external career-data skill (see Data layer below), which the plugin never contains. QA validates the one shipped artifact and confirms it holds zero personal data.
How to invoke: Spawn the QA agent by reading agents/qa-plugin.md and following its instructions. Pass it the repo path and the built .plugin.
This gate applies to: any content edit, any rename, any new file, any property name change, any structural change, any cross-version sync. If you edited even one file, run QA.
⛔ NO SILENT CAPABILITY REMOVAL — every removal needs a quoted user instruction
Removing, disabling, or substituting-away any capability the user relies on — an input an agent reads (a file, an archive, a database property), an output an agent produces, a pipeline step, a quality pass, or a read of the user's own material — requires the user's explicit instruction, quoted in the commit message and the changelog entry. "This new mechanism makes the old read unnecessary," "this is now redundant," "the consolidated file covers it" are NOT authorization — they are exactly how the incident below happened. Additions and tightenings can ride on an agent's judgment; removals never can. If a change you're making seems to imply a removal, stop and ask — the user deciding "yes, remove it" costs one question; a silent removal cost weeks of degraded output.
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.
- 7d ago First seen · 337 lines · 42,217 tokens per session scan B e0718938b566
career-engine CLAUDE.md is an instructions file published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 26d ago), licensed MIT. It adds 42,217 tokens to every session, about $0.2111 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.