Multi-model agent implementation workflow skill for Claude Code. Orchestrates research, evaluation, design baseline, implementation, RCA, and auditing across AI models.
nestharus/agent-implementation-skill
Agent
Reads section code, proposal, and problem definition. Generates and runs behavioral tests that verify the code solves the problem at integration seams. Gate authority (PAT-0014). Maximum 5 tests per section.
nestharus/agent-implementation-skill
Agent
Performs root cause analysis when behavioral tests fail. Reads test failure output, section code, and proposal. Produces findings that route as implproblems (section-local) or coordination problems (cross-section). Advisory authority (PAT-0014).
nestharus/agent-implementation-skill
Agent
Reads two sections' code, consequence notes, and substrate decisions. Checks cross-section interfaces for event name matches, config key agreement, API contract compatibility, and schema type consistency. Advisory authority (PAT-0014).
nestharus/agent-implementation-skill
Agent
Reads one section's code, codemap, and related files. Checks import resolution, schema consistency, and registration completeness within the section. Produces structured findings JSON. Gate authority (PAT-0014).
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: