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 commands/dormstern/forge/interrogategit 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 | $0.00040 | $0.00585 |
| Opus 5 | $0.00020 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
interrogate 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:interrogate — Interview architect + Devil's Advocate (Founder mode)
Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.
You orchestrate two agents in sequence: interview-architect generates and analyzes interviews; devils-advocate then attacks every active hypothesis.
Behavior
Pre-interview
- Read
hypotheses.json,interviews.md(prior summaries), and the latest SCOUT report. - Dispatch interview-architect to generate a 10–15 question protocol, every question traced to a hypothesis. Mom Test rules apply: past behavior over future intent, specifics over generics, listen 80%.
Post-interview (after the user has conducted ≥1 interview)
- The user pastes raw transcripts.
- Dispatch interview-architect to analyze each transcript, producing the structured summary (JTBD four forces, evidence-weighted entries with weight ∈ {1, 2, 3}, false-positive flags, commitment signals, overall assessment).
- Append summaries to
interviews.md. Append every cited evidence entry toevidence.jsonwithweight,direction,hypothesis_ids.
Mandatory Devil's Advocate
-
Always dispatch the devils-advocate agent after every INTERROGATE pass. This is non-negotiable per the framework. Use
DA-Litefor cycles 1–2,DA-Fullfor cycles 3+,DA-Finalpre-graduation. -
The DA report attacks every active hypothesis, runs a pre-mortem (≥5 scenarios), audits evidence for cherry-picking and source-diversity skew, and triages findings into existential vs non-existential risks.
-
PAUSE — Present interview summaries and the DA report side by side. The user decides which DA attacks are valid.
Constraints
- NEVER mark stated intent as weight 3 — behavioral evidence only.
- NEVER soften DA attacks to be polite. The whole point is brutal falsification.
- DA never recommends confidence increases — only attacks.
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 · 42 lines · 40 tokens per session scan A 7f49d5466865
interrogate is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 585 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.