Agents, Commands and Pipelines for Claude code & other harnesses
Command
Generates a coherent alternative frame for the problem an artifact solves — one that shares none of the artifact's assumptions. Not a competing solution but a competing understanding of the problem. Decision FRAMEAWARE/FRAMELOCKED.
Command
Finds terms and phrases used with multiple meanings within the same artifact. Produces a ranked ambiguity inventory with competing interpretations and disambiguation guidance.
Command
Reads from the position of someone afraid of the artifact's failure modes. Surfaces concerns hiding beneath confident language — classified by anxiety register (tactical/structural/epistemic). Decision CONFIDENCEWARRANTED/FRAGILITYMASKED.
Command
Run API Contract Validator to check consistency between docs, types, and implementation. Use after any API endpoint changes.
Command
Run Pre-Implementation Architect to validate design before coding. Reviews architectural fit, complexity, scope. Use BEFORE starting implementation.
Command
Performs Aristotelian four-cause decomposition on any artifact. Identifies material, formal, efficient, and final causes. Distinguishes essential from accidental properties. Decision TELEOLOGICAL/ATELEOLOGICAL.
Command
Surfaces implicit assumptions buried in any artifact — agent definitions, prompts, specs, plans, workflows, or documents. Produces a ranked assumption inventory with fragility scores.
Command
Compose the findings of upstream security agents into end-to-end attack chains. Validates each transition's exploitability in sequence, scores composed severity, annotates detection and containment gaps per stage, and identifies the single highest-leverage remediation. Decision - ISOLATED/CHAINABLE/CRITICALPATH.
Command
Deep runtime correctness audit. Catches async bugs, null dereferences, silent failures, and edge cases that pass all other validators. Use as FINAL gate before ship.
Command
Models someone who must use the artifact with no exit option. Surfaces friction invisible to voluntary feedback — unreported abrasions, workaround ecosystems, and enshittification risk from absent exit discipline. Decision EXITAVAILABLE/CAPTIVE.
Command
Traces execution and communication chains end-to-end through codebases. Given an entry point (concept, endpoint, function, event), follows every hop, transformation, and handoff to produce a complete chain map.
Command
Diagnose why a system survives failure. Attributes observed resilience behavior to the mechanism that actually carries it (ENGINEERED / COMPENSATED / FORTUITOUS), detects masking layers and load-bearing luck. Consumes upstream chaos-explorer/chaos-validator findings when provided; discovers read-only when not; runs…
Command
Survey the failure surface and produce a prioritized chaos-experiment agenda. Partitions the system into failure domains, classifies rehearsal depth (REHEARSED / DEFENDED-UNREHEARSED / UNDEFENDED), and identifies failure classes the existing resilience posture is silent on. Proposes experiments, never executes them.
Command
Project a system's resilience trajectory. Consumes upstream chaos-family artifacts (or discovers read-only) and projects luck-exhaustion, masking-collapse, rehearsal-decay, and fragility-accumulation trajectories — anchored to present-state evidence, condition-triggered (never dated), each with an early-warning signal…
Command
Validate system resilience through live fault injection and failure simulation. Tests dependency failures, network disruptions, resource exhaustion, timeout handling, and recovery behavior through actual chaos experiments.
Command
Validates code quality, standards compliance, and test coverage. Use after each implementation phase.
Command
Performs Confucian relational trajectory projection on any artifact. Projects naming drift, ritual decay, and relational entropy over time. Decision HIGHCONFIDENCE/MODERATECONFIDENCE/LOWCONFIDENCE.
Command
Assesses privacy compliance posture of data processing practices against applicable regulations (GDPR, CCPA/CPRA, HIPAA, COPPA, FERPA). Multi-jurisdiction assessment with legal basis mapping, consent evaluation, cross-border transfer analysis, and data subject rights coverage. Decision LAWFUL/UNCERTAIN/NONCOMPLIANT.
Command
Deep codebase exploration using grepai semantic search and call graph tracing. Produces structured exploration reports with traced relationships and architecture mapping.
Command
Performs foundational architecture analysis on any artifact. Traces derivation chains to terminal foundations, classifies each as DEDUCIBLE/CORROBORATED/CONVENTIONAL/SMUGGLED/OPAQUE, and maps declared-vs-actual architecture divergence. Decision TRANSPARENT/OPAQUE.
Command
Validates comprehensive documentation quality including JSDoc/TSDoc, API specs, changelog, and markdown. Complements public-interface for projects with significant documentation.
Command
Developer advocate gate for real user experience testing. Runs README examples, validates error quality, tests all functionality. The "would I recommend this?" check.
Command
Analyzes historical validation data to identify improvement patterns, regression triggers, and convergence velocity across the agent ecosystem. Uses RAH MCP tools for statistical analysis and uluops-tracker for raw data access.
Command
Identifies what a well-formed artifact of this type should contain but doesn't. Produces a ranked gap inventory with structural and linkage gaps and impact assessments.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: