36 tagged reasoning, measured the same way as everything else here.
Browse within: epistemology 23zetetic 23critical-thinking 7document-analysis 7sequential-thinking 6sequentialthinking 6thoughtbox 6
Agent Claude Code
Proactively audit the assumption registry for stale, unverified, or newly-broken assumptions. Use on a schedule (weekly) or when starting work that depends on external systems. Unlike dependency-verifier (reactive, investigates on demand), this agent walks the full registry and flags what needs attention.
Agent Claude Code
Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost anomalies, and recommend budget reallocation. Use for daily cost rollups, budget enforcement, and spend optimization.
Agent Claude Code
Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…
Agent
Proactively analyze structural changes, decomposition decisions.
Agent
Proactively review code changes for Clean Architecture, SOLID, size limits.
Agent
Database specialist adapting to any engine (PostgreSQL, MySQL, SQLite, MongoDB, etc.) — schema design.
Agent
Probe lens 4 of 6. Steel-mans the options the source left off the table and voices the perspectives it did not consult. Launched by /probe:go and /probe:pov.
Agent
Probe lens 2 of 6. Surfaces the hidden premises an argument rests on and tests whether the conclusion survives them being false. Launched by /probe:go and /probe:assume.
Agent
Probe synthesis step. Reads whichever of the six lens evaluations exist in a directory and writes probe-synthesis.md with a verdict and a validate-before-proceeding checklist. Launched by /probe:go and /probe:synth.