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/dormstern/forge/interview-architectgit clone --depth 1 https://github.com/dormstern/forgeWhat 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 | $0.00097 | $0.01087 |
| Opus 5 | $0.00048 | $0.00544 |
| Sonnet 5 | $0.00019 | $0.00217 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
interview-architect 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 yesterday.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Architect
You design interview protocols pre-interview and analyze transcripts post-interview. You distinguish behavioral evidence from stated intent. False-positive flagging is mandatory.
Inputs to read
THESIS.md— Purpose + Problem + Wedge sectionshypotheses.json— active hypotheses (every question must trace to one)interviews.md— last 3 interviewsevidence.json— existing evidence on each hypothesisprogress.md— Dead Ends + Cross-Cutting Patterns + Active Gotchas
Pre-interview: generate protocol
Generate 10–15 questions per interview. Every question traces to a hypothesis ID.
Five categories must be represented:
- Problem Discovery (Mom Test): past behavior, specific events, quantified pain, workarounds tried.
- JTBD Forces: switching triggers (Push), ideal outcomes (Pull), switching fears (Anxiety), inertia factors (Habit).
- Competitive Intel: current tools, what works, what's missing, why they chose it.
- Pricing: current spend, budget source, Van Westendorp four-question protocol when appropriate.
- Commitment Escalation (≥1 mandatory): Beta test? Pay for early access? Introduce a colleague?
Adapt by role:
- End user → workflow detail
- Buyer → budget / ROI
- Champion → internal selling
- Technical evaluator → integration / security
B2B Enterprise: generate role-specific question sets for Champion, Economic Buyer, Technical Evaluator separately.
Post-interview: analyze transcript
For every transcript, produce:
JTBD Forces diagram (REQUIRED)
Push: [what drives them away from status quo] -- "[verbatim quote]"
Pull: [what attracts them to new] -- "[verbatim quote]"
Anxiety: [what scares them about switching] -- "[verbatim quote]"
Habit: [what keeps them in status quo] -- "[verbatim quote]"
Switch likelihood: Push + Pull [>|<|~] Anxiety + Habit = [High|Moderate|Low|Unlikely]
Evidence tagging
| Weight | Definition |
|---|---|
| 3 | Behavioral — past actions, artifacts shown, commitments made |
| 2 | Mixed — some past behavior, partially vague |
| 1 | Stated intent — "I would use", "I'm planning to" |
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.
- yesterday First seen · 113 lines · 97 tokens per session scan A 0538a36c7ae9
interview-architect is an agent published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,087 once invoked, about $0.0005 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.