ai-coding agents

eugenelim/agent-ready-repo

Agent Claude Code

Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case). Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns severity-labeled findings. Use after gates pass but before declaring…

eugenelim/agent-ready-repo

Agent Claude Code

Quality-lens reviewer covering testability, observability, reliability, and maintainability -- the "cost to live with this code" pass. Also drafts contract or construction tests on request. Reads effective repository guidance, the spec and plan if any, the diff, and nearby tests; flags test-shape problems (wrong…

eugenelim/agent-ready-repo

Agent Claude Code

Threat-model and secure-design reviewer for changes that alter a security boundary, data flow, or guarding control — auth, data handling, dependency trust, deserialization, file/network controls, secrets, or LLM/agent authority and tool surfaces. Ordinary prompt wording with no authority, untrusted-input, tool…

pluginslab/wp-agentic-kit

Agent Claude Code

Sub-agents the main Claude Code agent can delegate to. Each one runs in its own context window, with its own restricted tool set, so the main agent stays focused.

pluginslab/wp-agentic-kit

Agent Claude Code

Audits a feature plan PR before human review — checks spec.md and plan.md against the planning conventions in PLANNING.md and the constitution's allowlists. Reports findings; never modifies files. Invoke during Phase 2.5 (plan freeze) of the wordpress-feature skill, after scripts/open-plan-pr.sh opens the plan PR and…

pluginslab/wp-agentic-kit

Agent Claude Code

Audits WordPress PHP and JavaScript for security issues against the project's SECURITY.md checklist. Reports findings; never modifies code. Invoke before merging any PR or shipping a release.

cogniplex/codemem

Agent

Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.

cogniplex/codemem

Agent

Wave 1 agent: creates baseline context memories for batches of source files and packages. Produces 1 memory per file + 1 per package, linked with PARTOF edges.

cogniplex/codemem

Agent

Maps a codebase using team-based deep analysis with priority-driven agent assignments. Use after initial project setup, when pending-analysis memories appear, or periodically to refresh the knowledge graph.

SienkLogic/plan-build-run

Agent

Part of pbr

Executes plan tasks with atomic commits, deviation handling, checkpoint protocols, TDD support, and self-verification.

SienkLogic/plan-build-run

Agent

Part of pbr

Creates executable phase plans with task breakdown, dependency analysis, wave assignment, and goal-backward verification. Also creates roadmaps.

SienkLogic/plan-build-run

Agent

Part of pbr

Goal-backward phase verification. Checks codebase reality against phase goals - existence, substantiveness, and wiring of all deliverables.

paullukic/coograph

Agent

Root-cause analysis, regression isolation, and build error resolution with minimal fixes.

paullukic/coograph

Agent

Interview-driven planning that produces actionable work plans with acceptance criteria.

paullukic/coograph

Agent

Reviews changes against project conventions, specs, and testing standards.

codeclawd/fable-mode

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

codeclawd/fable-mode

Agent

Compare two outputs WITHOUT knowing which skill produced them.

codeclawd/fable-mode

Agent

Evaluate expectations against an execution transcript and outputs.

richardcb/oh-my-gemini

Agent Gemini CLI

Code analysis and design agent for reviewing existing code, debugging complex issues, and designing system architecture. Use when the user wants to understand or evaluate code without making changes. Examples: "Review the authentication module for security issues" "Why is this API endpoint returning 500 errors?"…

richardcb/oh-my-gemini

Agent Gemini CLI

Task coordination agent. Analyzes requests, plans work, and uses skills to execute structured workflows. The primary agent mode for complex, multi-step tasks.

richardcb/oh-my-gemini

Agent Gemini CLI

Deep research agent for finding documentation, exploring APIs, and understanding concepts. Use when the user needs external context before making decisions. Examples: "What's the best way to handle JWT refresh tokens in Express?" "Find documentation on Gemini CLI's hook system" "Research best practices for database…

jmylchreest/aide

Agent

Part of aide

UI/UX design and frontend implementation specialist.

jmylchreest/aide

Agent

Part of aide

Focused implementation executor.

jmylchreest/aide

Agent

Part of aide

Quality assurance and testing specialist.