Scenario Critic — Project Management agent for Claude Code
Obtains an independent judgment on whether the planner's evidence scenarios are honest — not tailored to the solution, no leak of the answer into the task or the surface, falsifiable, on the requireme.
How to install Scenario Critic
Installs to ~/.claude/agents/seretos-agents-agent-autonomous-prompt-engineer-scenario-critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/seretos-agents/agent-autonomous-prompt-engineer/HEAD/agents/scenario-critic.md -o ~/.claude/agents/seretos-agents-agent-autonomous-prompt-engineer-scenario-critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Scenario Critic does
name: scenario-critic description: Obtains an independent judgment on whether the planner's evidence scenarios are honest — not tailored to the solution, no leak of the answer into the task or the surface, falsifiable, on the requirement — by running the bundled isolated critic (one separate Claude CLI process with no project context, no tools, no MCP) plus the mechanical scenario checks, and returns the merged findings. The only critic-like role in process-prompt-engineer. Never judges word
Alternatives in Project Management
- Suede Graph Flo XR Web Reader — Read-only Suede Graph Flo XR researcher for public web evidence, with no local file, shell, write, task, skill 139 ★
- Paper Critic — Adversarial auditor for LaTeX papers 130 ★
- Parallelizer — PROACTIVELY use this agent for concurrent execution of multiple independent tasks to improve performance 52 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Ndv Honest
Pure communication layer. Direct, ruthless, zero filler. Use for any task — cross-domain judgment, tradeoffs,
Kernel Completeness Critic
Specialist critic for linux-kernel-dev answers · scores ONLY completeness — error handling, cleanup paths, the
Kernel Correctness Critic
Specialist critic for linux-kernel-dev answers · scores ONLY correctness — does the answer actually solve the
Token Economy Agent
Cost-Classification Auditor. Owns whether a proposed recurring mechanism (per-sprint or per-commit) should be
Codeindexer Explorer
Proactively use for read-only discovery and reconstruction when independent evidence or context isolation has
Worca Cc Planner
Planner for the orchestrator pipeline. Operates in two modes — CLARIFY (surface the open decisions the planner
Related Skills
Resume Consultant Harness
Tailored-resume Claude Code skill using Planner → Generator → Evaluator harness with Zero AI Slop policy and i
Scenarios
Application Scenario Map
Future Scenario Generator
Generate comprehensive future scenarios with plausibility scoring, trend integration, and strategic implicatio