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 agents/andreaskarz/vibe-coding-dev-setup/hotchocolateexpertgit clone --depth 1 https://github.com/AndreasKarz/Vibe-Coding-Dev-SetupWhat 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 | $0.00059 | $0.01001 |
| Opus 5 | $0.00030 | $0.00500 |
| Sonnet 5 | $0.00012 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
HotChocolate Expert 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 97 lines · 59 tokens per session scan A ae8d77531e9a
HotChocolate Expert is an agent published in the GitHub repository AndreasKarz/Vibe-Coding-Dev-Setup (7 stars, last pushed 6mo ago), with no licence file. It adds 59 tokens to every session and 1,001 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 agents, from other repositories
Technical Program Manager
Manages project planning, timeline coordination, and cross-team communication. Also owns the business half of requirements engineering — structured stakeholder elicitation, user stories, acceptance criteria, scope definition, and the Definition of Ready gate before handoff to the Architect.
Architect
Designs system architecture, defines technical strategy, ensures long-term code quality, and owns the technical half of requirements engineering — system impact analysis, data flows, process modelling, and traceability from business intent to system design.
Platform Architect
Owns TOGAF Phase D and E. Derives Integration Requirements (IRs) and Technical Requirements (TRs) from ratified FRs/NFRs/SRs, owns the runtime topology, and ensures no technical artifact exists without a verified solution-layer parent.
Business Architect
Owns TOGAF Phase A/B. Elicits and ratifies business drivers (BRs), defines measurable business outcomes, and is the only persona allowed to author the root layer of the requirement cascade.
Solution Architect
Owns TOGAF Phase C. Derives FRs and NFRs from ratified BRs, owns the data architecture and application-layer specifications, and ensures every solution-layer artifact carries a verified parent link.
Security Engineer
Ensures security compliance, identifies vulnerabilities, and implements secure practices.