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/itsribbz/godspeed/profteamnpx skills add itsribbZ/Godspeed --skill profteamgit clone --depth 1 https://github.com/itsribbZ/GodspeedWrote 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/itsribbz/godspeed/profteam)<a href="https://agentmods.dev/skills/itsribbz/godspeed/profteam"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/profteam.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 | $0.00048 | $0.07072 |
| Opus 5 | $0.00024 | $0.03536 |
| Sonnet 5 | $0.00010 | $0.01414 |
| Haiku 4.5 | $0.00005 | $0.00707 |
Grade A, and why
profTeam 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 4d 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProfTeam v4.0 — Adaptive Multi-Agent Research & Refinement Engine
Pipeline Overview
Phase 0 (Classify + Pre-flight) → Phase 1 (Deploy Adaptive Agents, parallel) → Phase 1.5 (Validate + Recover) → Phase 2 (Cross-Reference + DevTeam Gate) → Phase 3 (Beta PDFs) → Phase 4 (Smart Cycle) → Phase 5 (Master PDF) → Phase 6 (Learnings + ROI)
When to Trigger
- User says "profTeam", "deploy profTeam", "run profTeam", "use profTeam on [topic]"
- User says "deep research", "heavy research", "comprehensive research"
- User says "multi-agent research on [topic]"
- A topic is too large or too critical for a single Professor pass
- When the Holy Trinity's Phase 2 targets profTeam with specific diagnostic gaps
Topic Classification Engine (v2.0)
Before deploying agents, classify the topic to auto-select the optimal agent configuration. Classification is based on the topic + accumulated ROI data from _learnings.md.
Topic Types & Default Agent Configs
| Topic Type | Detection Signal | Default Agents | Mandatory | Optimal Count |
|---|---|---|---|---|
| Architecture | "system", "design", "component", "architecture" | A:Theory, B:UE5/Impl, C:Industry, D:Pitfalls, F:CrossSystem | D | 5 |
| Debugging | "bug", "fix", "broken", "not working", specific error | A:Theory, B:Impl, D:Pitfalls, E:Codebase | D, E | 4-5 |
| Performance | "fps", "optimize", "memory", "draw calls", "lag" | A+C:Merged(Theory+Industry), B:Impl, D:Pitfalls, E:Codebase | D | 4 |
| Game Design | "gameplay", "mechanic", "combat feel", "player experience" | A:Theory, C:Industry, D:Pitfalls, E:Experimental | D | 4-5 |
| Product/Business | "market", "competition", "revenue", "pricing" | A:Market, B:Users, C:Tech, D:Pitfalls, E:Growth | D | 5-6 |
| Networking | "multiplayer", "replication", "server", "sync" | A:Theory, B:UE5Net, C:Industry, D:Pitfalls, E:Security | D | 5 |
| Broad/Unknown | Cannot classify | A:Theory, B:Impl, C:Industry, D:Pitfalls | D | 4 |
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.
- 4d ago First seen · 513 lines · 48 tokens per session scan A 4c4ff0326d4f
profTeam is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 7,072 once invoked, about $0.0002 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
model-routing
Route work to the cheapest model tier that holds quality. Use when deciding which model or agent should handle a task, when the user asks about token economy / cost optimization, or when dispatching implementation, review, or test-run work to subagents.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.