732 tagged code-quality, measured the same way as everything else here.
Browse within: development-workflow 57architecture 55ai-pipeline 53autonomous-coding 53autofix 38developer-productivity 37Multi-Agent 34ai-code-review 33AI Safety 30contracts 30agent-plugins 29antigravity 29bug-hunter 29javascript 28
Agent
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…
Agent
Code implementation specialist for refactoring workflows. Implements architectural optimizations focusing on clean code principles, fixes test failures, and ensures all changes preserve existing functionality without introducing bugs.
Agent
Internal dynos-work agent. Mandatory blocking auditor that enforces CLAUDE.md rules (local and global) against the task diff, spec, plan, and raw input. Cannot be skipped. Read-only. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from…
Agent
Agent "investigator-legacy" from dynos-fit/dynos-work, covering dynos-work investigator, ruthlessness standard, what you receive, what you do and step 1 — extract every clue from the prompt.
Agent
Internal dynos-work agent. Planner — handles discovery+design+classification, spec normalization, implementation plan + execution graph generation. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:start; never spawn this agent directly, from conversation, or outside a dynos-work task.
Agent
Use this agent to analyze code files against code quality standards after edits are made. This agent should be triggered proactively after code modifications when code-standards plugin is active. Context: The code-standards plugin is enabled and the user just finished writing a new TypeScript file. user: "I've added…
Agent
Use this agent when the user asks to "document compliance", "write security documentation", "create audit documentation", "document GDPR", "document SOC2", "document HIPAA", "write regulatory documentation", or needs documentation for compliance requirements, security controls, audit trails, or regulatory adherence.
Agent
STOP. Before doing ANYTHING else (including reading files), you MUST.
odere-pro/claude-oop-excellence
Agent
The plugin's central orchestrator across both audit tracks. Delegate when a project or component needs analysis or action over its code quality and design. Reads the glossary, resolves the caller's selection through the track → aspect → family/category/entity layers, then fans out one generic worker per in-scope…
odere-pro/claude-oop-excellence
Agent
Use to implement a single design pattern into a target scope with a safe parallel-change sequence, then verify with the project's own detected tests. The orchestrator injects one design-pattern record plus scope and an optional plan-only mode; this worker confirms the resolved issue is present, introduces the pattern…
odere-pro/claude-oop-excellence
Agent
Use to analyze design patterns in a target scope — detect which are already implemented (scan), judge where one would help (fit), or both in a single read. The orchestrator injects one design-pattern record — or a family batch of records — plus a lens (scan | fit | both), scope, and file manifest; this worker reads…
Agent
Implements exactly one Exolvra Genesis Task Spec, end to end. Use whenever the exolvra-genesis lead delegates a build round. Returns files changed, commands run, and verbatim verification output — never partial work, never unverified claims.
Agent
Blind, fresh-context judge for one Exolvra Genesis round. Use whenever the exolvra-genesis lead needs a verdict. Compares the real output against the captured bar, side by side. Verdict is WIN or LOSS with evidence; a tie is a LOSS.
Agent
Runs a full usability audit on an interactive mockup or prototype — derives personas and use cases, walks every workflow end to end, hunts for process gaps, audits AI-task progress visibility and content necessity, and writes a detailed usability report. Use when asked to usability-test, audit, or pressure-test a…
Agent
Deep, sourced web-research engine. Confirms every datum with ≥2 independent sources, extracts verbatim quotes, flags contradictions and unknowns. Output: findings+provenance JSON artifact (written to file) + one-line return. Shared worker for ds-research and ds-brief.
Agent
Delegate to this subagent when you need changeset@2 artifacts produced from a git diff. Input is a git diff, optionally a linked spec@1, and optionally smith's criteriaevidence from the TDD run that produced this diff. A diff spanning multiple independent topics produces one changeset@2 per topic, never one bundled…
Agent
Invoke once per candidate after scanner (and boundary-tracer for T7 or T10 candidates). Never batch multiple candidates in a single invocation. Input is one candidate@1 entry and the recon manifest; for T7 or T10 candidates, also receives the field survival map from boundary-tracer. The agent reads actual code at the…
Agent
Delegate to this subagent to execute exactly one task from a plan@1 via the full TDD cycle. Input is a single task object from a plan@1, a workspace manifest from recon, and optionally precisiontests from mutator. When specfilepath is set, reads the task's coverscriteria acceptance criteria from that file before…
Agent
Documentation audit agent. Validates README quality, ADR presence, Diátaxis coverage, and documentation/code drift.
Agent
Fusion audit agent. Combines Tier B (single-prompt synthesis + hotspot explorer) and Map-Reduce (12 parallel domain agents) into a single run for maximum finding recall. Deduplicates and correlates cross-architecture results.
Agent
Security audit agent. Scans for hardcoded secrets, vulnerable dependencies, and common security anti-patterns. Produces a domain report.
Agent Claude Code
Code investigator. Invoke when deep codebase research is needed. Explores in an independent context, returns a structured summary without polluting the main conversation.
Agent Claude Code
Code reviewer. Invoke after a modification plan is decided but before execution. Reviews plan soundness in an independent context.
afshinator/mcp-server-go-quality
Agent
This file tells AI agents how to use this MCP server. Load it once per session. For error handling tables, native output examples, and troubleshooting, see reference.md.