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 skills add spinningrachel/career-engine --skill role-prioritizergit 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/skills/spinningrachel/career-engine/role-prioritizer)<a href="https://agentmods.dev/skills/spinningrachel/career-engine/role-prioritizer"><img src="https://agentmods.dev/badge/skills/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/skills/spinningrachel/career-engine/role-prioritizer"><img src="https://agentmods.dev/badge/skills/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 | $0.00061 | $0.01101 |
| Opus 5 | $0.00030 | $0.00550 |
| Sonnet 5 | $0.00012 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
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 11d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Prioritizer — Doctrine
Why this pipeline has no rubric of its own
Prioritization exists to be cheap and fast, not to be a second brain. Every judgment call it makes — what counts as a good Priority score, what a Role Summary should contain, how to fetch a JD — already has a single authoritative source elsewhere in the plugin. Prioritization's entire discipline is: use those sources exactly as written, never approximate them, never maintain a lighter parallel version.
This is a deliberate, load-bearing design choice, not an oversight:
- Scoring doctrine drift is exactly the failure mode the plugin's cross-file-contracts table exists to prevent. Two scoring rubrics — even two nearly-identical ones — will diverge the first time either one is edited without the other in mind, and a role could get a different Priority depending on which pipeline touched it last.
- A second Role Summary content rule risks a Prioritization-written summary looking or reading differently from a coach-written one, which would be a visible seam to the user between "cheap triage" and "full research" output on the same property.
What Prioritization borrows, and from where
| Judgment | Source of truth | Prioritization's obligation |
|---|---|---|
How to score Priority |
01-writing-rules.md §1 — Priority Framework |
Apply the base criteria exactly, JD-only (no company/culture/landscape research — that's what full intake adds later). §1's requirements-coverage subsection is intake-only (2026-07-29) — it needs the full background read this pipeline deliberately skips; the coach re-scores with it and always overwrites |
| How to fetch a JD | career-engine-intake/SKILL.md Step 0.5 fetch ladder |
Reuse exactly — same fallback order, same fetch markers |
What a Role Summary looks like |
career-coach/coach-output.md → Output Format, the Role summary line |
Same ≤400-char, JD-vocabulary-only content rule |
| What counts as coach-complete | career-engine-intake/SKILL.md Step 0.8 |
Prioritization never writes enough fields to satisfy this list (it writes 5 of 13–14 required fields) — a role that only went through Prioritization must always still reach the coach |
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.
- 11d ago First seen · 40 lines · 61 tokens per session scan A 58177358fe72
role-prioritizer is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,101 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…