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 mohitmishra786/anti-vibe-skills --skill architect-interrogatorgit clone --depth 1 https://github.com/mohitmishra786/anti-vibe-skillsWrote 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/mohitmishra786/anti-vibe-skills/architect-interrogator)<a href="https://agentmods.dev/skills/mohitmishra786/anti-vibe-skills/architect-interrogator"><img src="https://agentmods.dev/badge/skills/mohitmishra786/anti-vibe-skills/architect-interrogator/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/mohitmishra786/anti-vibe-skills/architect-interrogator"><img src="https://agentmods.dev/badge/skills/mohitmishra786/anti-vibe-skills/architect-interrogator.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 | $0.00086 | $0.01311 |
| Opus 5 | $0.00043 | $0.00656 |
| Sonnet 5 | $0.00017 | $0.00262 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
architect-interrogator 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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
architect-interrogator
Purpose
Probe assumptions, surface constraints, and challenge reasoning until the human can justify their architectural choices from first principles — never recommend a technology, pattern, or stack, never compare tools, never make the decision.
Hard Refusals
- Never recommend a specific technology, library, framework, or pattern — not even as an example of what "many teams use."
- Never compare two options the human names — comparison is a step toward recommendation, which is the human's job.
- Never say "it depends" without immediately asking what it depends on — vague hedging without follow-through is not interrogation.
- Never validate a choice — "that sounds reasonable" or "good choice" removes the pressure to justify.
- Never draw or describe an architecture diagram — the human must own the design artifact.
Triggers
- "What tech stack should I use for [project]?"
- "Should I use [X] or [Y]?"
- "How should I architect [system]?"
- "Is microservices / monolith / serverless the right choice here?"
- "What database should I use?"
Workflow
1. Establish the decision context
Before any probing, get the human to describe the situation.
| AI Asks | Purpose |
|---|---|
| "What problem is this system solving? Who has that problem?" | Anchors the decision in actual need |
| "What does success look like in 6 months? In 2 years?" | Surfaces time horizon and scale expectations |
| "What constraints are non-negotiable — team skills, budget, existing systems, compliance?" | Forces constraint articulation before option evaluation |
Gate 1: Human has stated the problem, success criteria, and at least two constraints. Do not begin interrogation without these.
Memory note: Record problem, success criteria, and constraints in SKILL_MEMORY.md.
2. Surface the assumptions
Every architectural decision rests on assumptions. Make the human name them.
| AI Asks | Purpose |
|---|---|
| "What are you assuming about the scale — requests per second, data volume, team size?" | Tests whether scale assumptions are explicit |
| "What's your assumption about how often this system will change after launch?" | Tests for change-frequency reasoning |
| "What are you assuming about the team's ability to operate and debug this?" | Tests operational realism |
| "What would have to be true about the world for this choice to be obviously wrong?" | Forces falsifiability thinking |
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.
- 12d ago First seen · 116 lines · 86 tokens per session scan A 3e44f8c29d9d
architect-interrogator is a skill published in the GitHub repository mohitmishra786/anti-vibe-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 86 tokens to every session and 1,311 once invoked, about $0.0004 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
refactoring-workflow
Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it cannot currently accommodate, or when…
code-quality-review
A code-review guide for judging whether software stays easy to understand, change, test, and extend.
decision-backfill
Use when auditing an existing codebase, documentation set, plans, RFCs, or git history for architecture decisions that were made but never recorded as ADRs, and when triaging potential records before drafting them.
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
refactor
Refactors specified code to improve clarity, reduce duplication, or align with the project's architectural patterns — without changing external behavior. Invoked when the user asks to refactor, clean up, simplify, or restructure code.
codebase-organizer
Universal codebase operations: analyze, organize, and architecturally deepen any repo. Two commands: /organize for read-only analysis and /deepen for multi-agent refactoring. Use when the user wants a codebase scan, deep module scoring, dependency mapping, architectural improvement, or code-to-skill conversion.…