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
Decides whether a section needs a microstrategy breakdown before implementation. Reads section complexity signals and produces a structured yes/no decision with reasoning.
nestharus/agent-implementation-skill
Agent
Produces tactical per-file breakdowns from aligned integration proposals. Bridges the gap between high-level strategy and implementation by capturing what changes in each file, in what order, and why.
nestharus/agent-implementation-skill
Agent
Assesses landed section changes for governance-visible debt, pattern drift, and refactor requirements after implementation alignment passes.
nestharus/agent-implementation-skill
Agent
Re-explores sections that have no related files. Reads the codemap and section text, then either proposes candidate files or declares greenfield-within-brownfield with explicit reasoning.
nestharus/agent-implementation-skill
Agent
Combined problem alignment + philosophy alignment + passive surface discovery. Checks whether work stays coherent with both the section problem definition and operational philosophy, discovering misalignment surfaces as a side-effect.
nestharus/agent-implementation-skill
Agent
Meta-agent generator that produces per-section intent pack artifacts (seed problem definition with axis structure and alignment rubric) from section excerpts and code context.
nestharus/agent-implementation-skill
Agent
Cheap classification agent that decides between lightweight and full intent cycles based on section complexity signals.
nestharus/agent-implementation-skill
Agent
Optional bootstrap helper that reads project-shaping artifacts and suggests project-specific philosophy prompts for the user.
nestharus/agent-implementation-skill
Agent
One-time conversion of execution philosophy (freeform user intent) into operational philosophy (numbered principles with interactions and expansion guidance).
nestharus/agent-implementation-skill
Agent
Validates philosophy surfaces, classifies them by compatibility, integrates safe ones into operational philosophy, and gates the user for tensions or contradictions.
nestharus/agent-implementation-skill
Agent
Fast classifier that selects philosophy source files from a mechanical catalog of repository documents.
nestharus/agent-implementation-skill
Agent
Full-read verifier for all shortlisted philosophy source candidates. Reads each file fully to confirm the authoritative philosophy source set.
nestharus/agent-implementation-skill
Agent
Validates problem surfaces discovered by the intent judge and integrates confirmed ones into the living section problem definition and rubric axis table.
nestharus/agent-implementation-skill
Agent
Decomposes a project spec into a global proposal, global alignment document, and atomic section files for downstream pipeline stages.
nestharus/agent-implementation-skill
Agent
Ensures source files in the codespace have module-level docstrings.
nestharus/agent-implementation-skill
Agent
Runs full test suite, import verification, and prepares commit.
nestharus/agent-implementation-skill
Agent
Reviews constraints and tradeoffs at project level for promotion.
nestharus/agent-implementation-skill
Agent
Runs constraint alignment checks, linting, and tests against the codespace.
nestharus/agent-implementation-skill
Agent
Writes integration proposals as problem-state artifacts — capturing what is resolved, what is unresolved, and whether the section is ready for implementation. Explores strategically to populate the problem state, not to invent architecture.
nestharus/agent-implementation-skill
Agent
Extracts section-level excerpts from global proposal and alignment documents. Identifies the specific problems, constraints, and strategy relevant to a single section.
nestharus/agent-implementation-skill
Agent
Contract compliance interceptor. Evaluates task payloads against submitting and receiving agent contracts. Returns PASS or REJECT with structured rationale. Deliberately context-blind — judges only against written contracts.
nestharus/agent-implementation-skill
Agent
Evaluates ungrouped reconciliation candidates and decides which describe the same underlying concern. Returns structured merge verdicts for new-section candidates or shared seam candidates.
nestharus/agent-implementation-skill
Agent
Executes a single research ticket by searching the web and/or codebase for specific answers, producing a ticket result with citations and extracted constraints.
nestharus/agent-implementation-skill
Agent
Decomposes blocking research questions and intent surfaces into a structured research plan with fanout tickets, synthesis gates, and budget allocation.
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: