kangig94

33 mods across 1 repository, 11 stars between them.

coral

01

kangig94/coral

Plugin Claude Code

Claude Code plugin - structured agents with Codex and Claude CLI bridges.

11 yesterday A tokens not measured original MIT

code-critic

02

kangig94/coral

Agent Claude Code

Code quality reviewer. Evaluates elegance, complexity, pattern adherence, test coverage, and maintainability. Use after implementation. NOT for domain correctness (domain agents).

11 yesterday A 36 tokens original MIT

doc-critic

03

kangig94/coral

Agent Claude Code

Documentation quality reviewer. Evaluates structure, accuracy, completeness, actionability, and audience fit. Use when docs are generated or modified. NOT for code quality (code-critic).

11 yesterday A 40 tokens original MIT

hook-safety

04

kangig94/coral

Agent Claude Code

Hook timeout safety and Node.js ESM conventions reviewer. Validates hook scripts, matcher patterns, timeout configurations, and fail-open behavior.

11 yesterday A 31 tokens original MIT

kangig94/coral

Agent Claude Code

CLI/backend contract guardian. Validates command schemas, output contracts, error handling, and process lifecycle across Coral integrations.

11 yesterday A 27 tokens original MIT

skill-quality

06

kangig94/coral

Agent Claude Code

SKILL.md quality reviewer. Validates frontmatter correctness, argument-hint declarations, reference resolution, and protocol clarity.

11 yesterday C 27 tokens original MIT

test-critic

07

kangig94/coral

Agent Claude Code

Post-implementation test auditor. Verifies implemented tests against production behavior and rejects unnecessary, duplicate, brittle, or overengineered verification.

11 yesterday A 31 tokens original MIT

ux-critic

08

kangig94/coral

Agent Claude Code

Plugin UX reviewer. Evaluates cognitive clarity, discoverability, workflow composition, and progressive disclosure of Coral CLI commands, skills, and user-facing text.

11 yesterday A 34 tokens original MIT

tier-review

09

kangig94/coral

Skill Claude CodeCodex

Use after implementation to run tier-classified review agents and produce a consolidated verdict.

11 yesterday A 19 tokens original MIT

reef

10

kangig94/coral

Skill Claude CodeCodex

Launch the coral-reef dashboard (auto-install, build, and start).

11 yesterday A 17 tokens original MIT

coral

11

kangig94/coral

Plugin Claude Code

Claude Code plugin - structured agents with Codex and Claude CLI bridges, plus deterministic workflow orchestration.

11 yesterday A tokens not measured original MIT

architect

12

kangig94/coral

Agent

Architecture & debugging advisor. Use PROACTIVELY when reviewing code structure, design patterns, dependency analysis, or debugging complex issues. Also participates as a structural reviewer in the /plan protocol. NOT for requirements analysis (gap-finder).

11 yesterday A 49 tokens original MIT

critic

13

kangig94/coral

Agent

Plan & code change critic. Use PROACTIVELY when reviewing implementation plans, schema changes, or significant code modifications. NOT for code analysis (architect) or requirements gathering (gap-finder).

11 yesterday A 41 tokens original MIT

debugger

14

kangig94/coral

Agent

Systematic bug diagnosis via hypothesis testing, reproduction tracing, and root cause analysis.

11 yesterday A 19 tokens original MIT

gap-finder

15

kangig94/coral

Agent

Requirements gap analyst. Catches missing questions, undefined guardrails, scope risks, and edge cases before planning. Use PROACTIVELY when scoping new features, API changes, state lifecycle changes, or concurrency behavior modifications. NOT for project scanning (scanner), code debugging (debugger), or plan review…

11 yesterday A 68 tokens original MIT

persona-generator

16

kangig94/coral

Agent

Generate a diverse, differentiated discussion persona based on role and topic. Spawned in parallel by discuss-lead.

11 yesterday A 25 tokens original MIT

pioneer

17

kangig94/coral

Agent

Finds the most elegant form of any design or solution, regardless of cost.

11 yesterday A 19 tokens original MIT

red-attacker

18

kangig94/coral

Agent

Adversarial test generator - writes tests targeting blind spots the implementer missed.

11 yesterday A 20 tokens original MIT

resolver

19

kangig94/coral

Agent

Feedback synthesizer and contradiction resolver. Synthesizes reviewer findings using Vada frame, resolves constraint collisions via TRIZ, and applies changes directly to the plan file. Spawned by plan skill at step 4b. NOT for reviewing (architect/critic) or planning (plan skill).

11 yesterday A 60 tokens original MIT

scanner

20

kangig94/coral

Agent

Project scanner and process investigator. Maps architecture, traces dependencies, investigates systemic issues. Use for project understanding, repo analysis, or process-level root cause investigation. NOT for requirements gaps (gap-finder), code bugs (debugger), or code architecture review (architect).

11 yesterday A 55 tokens original MIT

workflow-literal

21

kangig94/coral

Agent

Pipeline step processor for inline prompt literals in workflow DSL. Executes user-provided instructions against pipeline context.

11 yesterday A 24 tokens original MIT

analyze

22

kangig94/coral

Skill Claude CodeCodex

Use when deep investigation is needed — project structure, requirement gaps, or root cause diagnosis. Supports --delegate.

11 yesterday A 25 tokens original MIT

bid

23

kangig94/coral

Skill Claude CodeCodex

Submit a bid or speech in an active --user discuss session.

11 yesterday A 14 tokens original MIT

bugfix

24

kangig94/coral

Skill Claude CodeCodex

Use when encountering a bug, error, or unexpected behavior that needs diagnosis and fix.

11 yesterday A 20 tokens original MIT