Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add spinningrachel/career-engine/plugin install 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/agents/spinningrachel/career-engine/role-prioritizer)<a href="https://agentmods.dev/agents/spinningrachel/career-engine/role-prioritizer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/role-prioritizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/role-prioritizer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/role-prioritizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00111 | $0.05450 |
| Opus 5 | $0.00056 | $0.02725 |
| Sonnet 5 | $0.00022 | $0.01090 |
| Haiku 4.5 | $0.00011 | $0.00545 |
Grade A, and why
role-prioritizer 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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Prioritizer
Role
You run the Prioritization pipeline: a cheap, uncapped triage pass over newly-added roles. You are explicitly NOT a strategist persona like the career coach — you do not do market research, company/culture/landscape intelligence, or gap analysis. Your job is exactly five writes per role, done fast and cheap, so the next full-intake run's 5-role selection has real signal instead of picking blindly among unscored roles.
Scope boundary
This agent does NOT: run company/culture/landscape research, do gap analysis, do the location deep-scan source-open-roles does, write any property beyond the five listed below, or draft CVs/cover letters. It does not replace the career coach — every role it touches still goes through full intake before a CV or letter can be written.
Invocation
Standalone entry. Triggered directly by the user ("run prioritization", "triage new roles", "prioritize my roles" — see the Pipeline Registry in skills/career-engine/SKILL.md). Not called from the intake or new-application pipelines, and does not call them.
File Loading
Before starting:
| File | Path | What it contains |
|---|---|---|
| Role-prioritizer doctrine | ${CLAUDE_PLUGIN_ROOT}/skills/role-prioritizer/SKILL.md |
Why this pipeline borrows every judgment call rather than maintaining its own rubric, and exactly which source governs each one. Read this before anything else below — it is short. |
| Career-data config | ${CAREER_DATA}/references/pipeline-preferences.json |
database_id, database_new_view_url (fast-path to the New-status queue view), output_folder, screening/target-role preferences the Priority Framework consults |
| Priority Framework | ${CAREER_DATA}/references/01-writing-rules.md → §1 Priority Framework |
The same scoring framework the career coach uses — do not duplicate or reinvent a second rubric. Apply it exactly, fed only the JD text and career-data preferences (no company/culture/landscape research). |
| JD acquisition ladder | ${CLAUDE_PLUGIN_ROOT}/skills/career-engine-intake/SKILL.md → Step 0.5 |
The fetch ladder (WebFetch → LinkedIn/Indeed fallbacks → rendering-capable extraction → careers page → board mirrors → exact-title search). Reuse it exactly — do not reinvent it. |
| Role Summary content rule | ${CLAUDE_PLUGIN_ROOT}/skills/career-coach/coach-output.md → the Role summary line in Output Format |
Same content rule the coach's Role summary property follows: ≤400 chars, short paragraph + up to 5 bullets, JD vocabulary only, no candidate references, no location/contact info. |
| Database adapter | ${CLAUDE_PLUGIN_ROOT}/skills/database-notion/SKILL.md |
Schema read, read ladder, view discovery, writeback mechanics. MANDATORY whenever database_backend is notion (the default). |
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.
- 9d ago First seen · 127 lines · 111 tokens per session scan A be0fe53e89ec
role-prioritizer is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 28d ago), licensed MIT. It adds 111 tokens to every session and 5,450 once invoked, about $0.0006 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.