professional-role-router

professional-role-router is a skill for Codex from markoblogo/abvx-agent-skills. It costs 68 tokens per session (643 once invoked), scanned A, original, MIT.

A workflow for assigning a substantial task to one main professional perspective and, when needed, up to two supporting perspectives. It passes a concrete work item, such as a brief, draft, issue, patch, or review, between them.

In plain words
What is it for?
It is for routing career, research, publishing, coaching, business, finance, support, architecture, and software tasks to suitable specialist approaches.
Why use it?
It reduces unfocused role-play and duplicated effort by choosing who owns the deliverable and what supporting work is required. It also keeps handoffs explicit.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for routing career, research, publishing, coaching, business, finance, support, architecture, and software tasks to suitable specialist approaches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markoblogo/abvx-agent-skills/professional-role-router
Install

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.

Any agent
npx skills add markoblogo/abvx-agent-skills --skill professional-role-router
Clone the repo
git clone --depth 1 https://github.com/markoblogo/abvx-agent-skills

Made for: Codex.

Wrote 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.

agentmods badge for professional-role-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/professional-role-router/github.svg)](https://agentmods.dev/skills/markoblogo/abvx-agent-skills/professional-role-router)
Your own site
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/professional-role-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/professional-role-router/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.

agentmods 80×15 button for professional-role-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/professional-role-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/professional-role-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00643
Opus 5 $0.00034 $0.00321
Sonnet 5 $0.00014 $0.00129
Haiku 4.5 $0.00007 $0.00064

Measured 3d ago against content hash 4c268ea208ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

professional-role-router 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 3d 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.

skills/professional-role-router/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Professional Role Router

Use professional roles to improve the work, not to stage a role-play performance.

Route

  1. Identify the current deliverable, domain, evidence needs, and action risk.
  2. Choose one primary professional responsible for that deliverable.
  3. Add at most two supporting roles when their outputs are explicit dependencies.
  4. Load only the relevant domain context, sources, and role guidance.
  5. Complete the task in the primary role's working mode: advise, research, draft, review, or implement.
  6. Pass a compact artifact between roles: evidence pack, brief, draft, issue, patch, review, or release packet.
  7. Return control to the coordinator or user when the deliverable is complete or a gate is reached.

Selection Examples

  • Job search: career advisor primary; researcher for company/market evidence; coach for interview practice or accountability.
  • Book production: researcher primary for buyer/search evidence; writer for manuscript; publishing manager for packaging and platform state.
  • Software work: architect for boundaries and trade-offs; senior engineer for implementation; reviewer/test engineer for proof.
  • Personal support: personal coach for goals and habits; wellbeing coach for emotional reflection; fitness coach for training.
  • Business or finance: strategist for options; researcher for evidence; financial professional for budgets, forecasts, or reconciliation.

Use project-specific roles when they exist. Domain manuals, repository rules, professional policies, and current evidence override generic role patterns.

Boundaries

  • Role selection changes stance, context, and deliverable shape. It does not grant tools, memory, permissions, credentials, or autonomy.
  • Do not load an entire role catalog or combine many personas in one prompt.
  • Do not invent qualifications, facts, legal/medical conclusions, financial certainty, or domain authority.
  • Separate advice, drafting, isolated execution, external action, and public verification.
  • Keep personal and project-private context in their permitted scope; cross-role handoff carries only what the next role needs.
  • Ask the user only when route ambiguity changes privacy, cost, authority, or the requested outcome.

Read the full file on GitHub · 52 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 52 lines · 68 tokens per session scan A 4c268ea208ef

Subscribe to this mod's changes

professional-role-router is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 643 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 2026-09-09.