hg-pyun

37 mods across 1 repository, 2 stars between them.

hg-pyun/claude-code-marketplace

Instructions file

Instructions for hg-pyun/claude-code-marketplace, covering claude-code-marketplace — maintainer guide, 30-second picture, directory layout, workflows index and authoring rules (repo-wide).

2 1mo ago A 2,918 tokens original MIT

buddy

03

hg-pyun/claude-code-marketplace

Plugin Claude Code

Thinking-partner skills that keep the pen in your hand: a Socratic design interview and a predict-then-verify codebase reader.

2 1mo ago A tokens not measured original MIT

grok-codebase

04

hg-pyun/claude-code-marketplace

Skill Claude CodeCodex

A predict-then-verify + explain-back reading partner for UNFAMILIAR code, so the structure actually lodges in your head instead of evaporating with an AI summary. Instead of summarizing the code for you, it picks a spot, makes you PREDICT what it does (or who calls it, or what happens) via one AskUserQuestion, then…

2 1mo ago A 276 tokens original MIT

dev-tools

05

hg-pyun/claude-code-marketplace

Plugin Claude Code

Multi-agent dev toolkit: orchestration, code review, git/GitHub workflows, and debugging.

2 1mo ago A tokens not measured original MIT

analyst

06

hg-pyun/claude-code-marketplace

Agent

Read-only requirements analysis advisor. Surfaces hidden constraints, surfaced assumptions, and ambiguity from an idea or spec; produces a scored requirement decomposition. Use when a skill needs structured requirement clarity before planning or design begins.

2 1mo ago A 45 tokens original MIT

architect

07

hg-pyun/claude-code-marketplace

Agent

Read-only system design and trade-off advisor. Analyzes architecture, evaluates interface contracts, and recommends structural changes with file:line evidence. Use when a skill or agent needs an independent design or architectural opinion — not for root-cause bug diagnosis (use debugger) or completion verification…

2 1mo ago A 66 tokens original MIT

code-simplifier

08

hg-pyun/claude-code-marketplace

Agent

Behavior-preserving simplification agent. Refactors code within a given changed-file set for clarity and maintainability — zero observable behavior change, zero scope expansion. Consumed by ralph (Step 7.5) and team cleanup passes.

2 1mo ago C 53 tokens original MIT

debugger

09

hg-pyun/claude-code-marketplace

Agent

Read-only root-cause analysis advisor. Diagnoses WHY build/test/runtime failures occur, applies a 4-phase RCA protocol, and hands off a concrete hypothesis with file:line evidence. Use when a skill needs root-cause diagnosis before handing off a fix to executor.

2 1mo ago A 58 tokens original MIT

doc-writer

10

hg-pyun/claude-code-marketplace

Agent

Documentation domain advisor — analyzes docs for gaps, staleness, and inconsistencies; writes or edits directly when invoked autonomously.

2 1mo ago A 30 tokens original MIT

executor

11

hg-pyun/claude-code-marketplace

Agent

Focused code-implementation agent. Implements code changes precisely as specified, autonomously explores and plans multi-file changes, and verifies with fresh test/build output. Enforces the TDD Iron Law (refuses to write production code without a failing test). After 3 failed attempts, escalates to architect…

2 1mo ago C 74 tokens original MIT

explorer

12

hg-pyun/claude-code-marketplace

Agent

Fast read-only search for files, symbols, and patterns across a codebase. Returns absolute paths and concise excerpts. Use when another skill needs to locate where something lives before acting on it.

2 1mo ago A 41 tokens original MIT

git-master

13

hg-pyun/claude-code-marketplace

Agent

Domain-layer git operations agent. Encapsulates status inspection, diff analysis, staging, commit message construction, rebase, and history traversal as a reusable layer that the git-rebase-stack command delegates to (the git-commit and github-pr skills intentionally handle their git mechanics inline). Performs…

2 1mo ago A 91 tokens original MIT

performance-analyst

14

hg-pyun/claude-code-marketplace

Agent

Read-only performance domain advisor — identifies hotpaths, complexity issues, IO/Memory/Cache anti-patterns with severity-rated findings and file:line evidence.

2 1mo ago A 36 tokens original MIT

planner

15

hg-pyun/claude-code-marketplace

Agent

Read-only task sequencer. Turns a spec or PRD into an ordered execution plan — story breakdown, dependency DAG (dependsOn), file scope, and testable acceptance criteria. Use when a skill needs a structured plan with sequencing and dependencies before execution begins.

2 1mo ago A 54 tokens original MIT

reviewer

16

hg-pyun/claude-code-marketplace

Agent

Severity-rated review of diffs, docs, or files. Returns CRITICAL/MAJOR/MINOR findings with file:line evidence. Trigger when another plugin or skill needs an honest second-pass review of changes.

2 1mo ago A 46 tokens original MIT

security-auditor

17

hg-pyun/claude-code-marketplace

Agent

Security domain advisor — surfaces AuthN/AuthZ/Secret/Crypto/Injection/SAST/Config findings with severity and confidence ratings.

2 1mo ago A 31 tokens original MIT

test-engineer

18

hg-pyun/claude-code-marketplace

Agent

Test strategy, integration/e2e coverage, flaky test hardening, and TDD enforcement. Writes failing tests first, diagnoses coverage gaps with risk levels, and refuses to advance to implementation until a Red test exists. Use when a skill needs the Red step of Red-Green-Refactor, coverage analysis, or flaky-test…

2 1mo ago A 71 tokens original MIT

tracer

19

hg-pyun/claude-code-marketplace

Agent

Evidence-driven causal tracing agent. Reverse-traces from an observed effect (HTTP response, log line, stack trace, wrong output) back through the codebase to the responsible code, comparing competing hypotheses with supporting and refuting evidence. Hands a ranked hypothesis list and evidence chain to downstream…

2 1mo ago A 72 tokens original MIT

verifier

20

hg-pyun/claude-code-marketplace

Agent

Read-only completion-verification agent. Runs the standard verification protocol (BUILD/TEST/LINT/FUNCTIONALITY/TODO/ERRORFREE) with fresh, pasted command output and returns a machine-readable verdict. Use when a caller needs definitive done-ness confirmation backed by evidence, not opinion.

2 1mo ago A 61 tokens original MIT

git-rebase-stack

21

hg-pyun/claude-code-marketplace

Command

Clean up stacked branches via git rebase --onto --update-refs when the base changes, a middle PR merges or drops, or the whole stack needs to re-sync. Auto-detects the stack from the current branch when no argument is given. TRIGGER when: user mentions stacked PR rebase, base branch change, stack cleanup, or says…

2 1mo ago A 151 tokens original MIT

autopilot

22

hg-pyun/claude-code-marketplace

Skill Claude CodeCodex

End-to-end 5-phase pipeline from idea to code-ready state — analyst intake → ralplan → ralph/team → verifier-gated QA → multi-perspective validation. Artifacts land in .dt-handoff/ /. Auto commit/PR PROHIBITED. TRIGGER on "/autopilot", "autopilot", "build me", "create me", "make me", "I want a/an". DO NOT TRIGGER for…

2 1mo ago A 104 tokens original MIT

code-review

23

hg-pyun/claude-code-marketplace

Skill Claude CodeCodex

Severity-rated review of the current diff or a named file. Always delegates to the reviewer agent, and routes security-auditor + doc-writer onto the panel when the diff touches their surface (full panel in slug context), producing CRITICAL/MAJOR/MINOR findings with file:line evidence. TRIGGER when user says "review my…

2 1mo ago A 104 tokens original MIT

curl-debug

24

hg-pyun/claude-code-marketplace

Skill Claude CodeCodex

Execute a cURL command and trace the response back through the codebase to find the root cause of bugs. Use this skill to debug API issues by running the actual request and reverse-tracing from the response to the responsible code. TRIGGER when: user shares a cURL command along with a question about a bug, error, or…

2 1mo ago A 195 tokens original MIT