agentflow-grill-me
Agentflow Grill Me
Interview the user relentlessly until the plan is ready to write. Walk the decision tree one dependency at a time and resolve ambiguities before planning.
Rules
- Ask one question at a time, then wait for the user's answer.
- For every question, provide your recommended answer and why.
- If the answer can be found by reading the codebase, docs, existing plans, prior evals, or Agentflow graph/runtime contracts, inspect those sources instead of asking.
- Treat short answers like "yes" or "agree" as acceptance of your recommendation, then move to the next unresolved branch.
- Challenge vague goals, hidden dependencies, unclear authority, missing validation, unclear artifacts, prompt/context bloat, and supervisor or harness assumptions.
- Keep track of resolved decisions, open decisions, risks, and dependencies as the interview proceeds.
- Stop grilling only when there is enough shared understanding to write a concrete plan.
Finish
When the decision tree is resolved, summarize:
- the agreed goal and non-goals
- the chosen design and rejected alternatives
- the remaining assumptions or risks
- the validation/eval plan
- the first implementation slice
Then create the plan if the user asked for one, or ask for permission to write it.
More from koji98/agentflow
agentflow
Use when authoring, validating, running, inspecting, or debugging supervised Agentflow graphs, managed patterns, plugin tools, delivery packages, supervisor interventions, or Codex/Cursor harness behavior.
10agentflow-plugins
Use when creating, reviewing, resolving, or consuming Agentflow plugin workflows or plugin-bundled CLI tools, including workflow manifests, lockfiles, tool config, and credential policy.
6agentflow-run-debugging
Inspect, explain, and debug Agentflow runs. Use when a run failed, resumed unexpectedly, or needs artifact-level diagnosis; when tracing state.json, events.jsonl, execution logs, context packets, or execution artifacts; or when deciding why passed work did or did not preserve on resume.
3agentflow-graph-authoring
Design, review, and refine Agentflow execution graphs. Use when authoring or editing Agentflow graph JSON, choosing between primitive nodes and managed workflows, or checking topology, profiles, context flow, outputs, and validation against the shipped runtime contract.
3agentflow-managed-workflows
Author and review Agentflow managed workflows. Use when choosing between deep_research, spec_design, execute_spec, and review_change, or when filling their brief, context_policy, approval_policy, strategy, delivery, and runtime fields.
3agentflow-evals
Use when designing, validating, running, inspecting, or improving Agentflow eval suites, scenarios, variants, criteria, environment simulation, trajectory checks, trace packets, scorecards, benchmark reports, prompt-pack experiments, dogfood workflow-quality evals, capability-workflow local repo evals, or pinned real-world GitHub issue evals.
2