coding-agent agents

147 tagged coding-agent, measured the same way as everything else here.

Browse within: GLM 52codex-cli 47ai-coding-agent 42agentic-ai 39cli 28json-rpc 22claude-code-plugin 20agent-orchestration 18context-engineering 18terminal-ui 15tui 15agentic-framework 14desktop-app 13ai-coding 12

test-engineer

01

QwenLM/qwen-code

Agent Claude Code needs its repo ✓ vendor

Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…

not rated 29k +123 today A 119 tokens original Apache-2.0

softaworks/agent-toolkit

Agent Claude Code

Mermaid diagram specialist for creating flowcharts, sequence diagrams, ERDs, and architecture visualizations.

not rated 2.6k +14 7mo ago A 26 tokens original MIT

deep-researcher

03

Human-Agent-Society/CORAL

Agent Claude Code needs its repo

Deep researcher — spawn to conduct thorough web research on the problem domain, save raw sources, and write structured findings. Use proactively when starting a new task, when scores plateau, or when the team needs fresh ideas from literature.

not rated 1.1k +12 1mo ago B 50 tokens original Apache-2.0

DevCodex Auto

04

devcodex-labs/devcodex

Agent Claude Code

An AI development-rules assistant with an automatic mode that can be enabled explicitly or through configured aliases. It keeps that mode active during a conversation and can proceed automatically in approved paths while enforcing safety rules.

not rated 438 +1 changed 1mo ago A 55 tokens AGPL-3.0

code-explorer

05

get-vix/vix

Agent Claude Code

Explores a codebase for the whiteboard/voice experience. Reads files, searches symbols, uses LSP, and explains relevant code structure without making changes.

not rated 282 +1 23d ago A 36 tokens AGPL-3.0

web-researcher

06

KonghaYao/peri

Agent Claude Code

Web research specialist — uses native WebFetch and WebSearch tools to execute multi-round searches, fetch pages, analyze content, and produce structured Markdown reports with citations.

not rated 240 +15 today A 41 tokens original Apache-2.0

loop-verifier

07

eli-labz/Godcoder

Agent Claude Code

Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.

not rated 181 1mo ago A 25 tokens

doc-writer

08

rojim666/SztuCode

Agent Claude Code

A writing-stage agent that receives a request, chooses a suitable writing guide, and coordinates its use. It returns Markdown as an internal draft for later formatting, not as the final document.

not rated 110 +2 yesterday A 110 tokens original MIT

marconae/speq-skill

Agent Claude Code

Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.

not rated 55 changed 3d ago A 38 tokens original MIT

bug-reproducer

10

AbyssCN/oh-my-dag

Agent Claude Code

A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.

not rated 43 +1 5d ago A 31 tokens original MIT

Explore

11

ilovepixelart/pi-code

Agent Claude Code

Fast read-only codebase exploration that returns compressed findings.

not rated 35 +1 2d ago A 12 tokens original MIT

reviewer

12

bacnh85/pi-extensions

Agent Claude Code

Code review specialist. Use for correctness, security, regression, and meaningful test-gap review.

not rated 33 changed 1mo ago A 21 tokens

bgrenat/godot-game-dev-studio

Agent Claude Code

Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.

not rated 20 +2 4d ago A 42 tokens LGPL-3.0

LeanAndMean/scramjet

Agent Claude Code

Analyzes type design for encapsulation quality, invariant expression, usefulness, and enforcement, providing quantitative ratings and actionable improvement suggestions.

not rated 8 6d ago A 31 tokens original Apache-2.0

ctf

16

zebbern/termstack

Agent Claude Code

CTF Coordinator — Triages CTF challenges by category and delegates to specialized agents (web, crypto, forensics, binary, reversing, misc, bonus). user-invocable: true argument-hint: 'Challenge info — e.g.

not rated 4 6mo ago A 53 tokens

FI-Mihej/codebase-agent-mcp

Agent Claude Code

Start codebase analysis. Analyze single entity/action only. Return detailed analysis, recommendations, implementation guidance, usage examples. Prefer dependencylibraries-related-files-search first. Provide all relevant context (files, paths, symbols, imports, etc.). One topic or one context per request → wait for the…

not rated 3 +1 14d ago A 127 tokens original Apache-2.0

kimtth/ms-fabric-skills-dev-starter

Agent Claude Code

Orchestrate end-to-end workload migration from Azure Synapse Analytics, Azure HDInsight, or Databricks to Microsoft Fabric. Handles migration assessment, phased execution planning, utility API porting (mssparkutils/dbutils → notebookutils), connectivity migration (Linked Services/mounts → Data Connections/OneLake…

not rated 2 4mo ago A 143 tokens

git

19

dineshdb/pie

Agent Claude Code

Git history specialist — surgical commits with honest messages, history inspection (log/diff/blame/reflog), and when/why/who questions answered from evidence.

not rated 2 19d ago A 35 tokens original MIT

css

20

lfyxhappy/lfcode

Agent OpenCode

Agent "css" from lfyxhappy/lfcode, covering example of correct implementation, reusable components and key clarifications.

not rated 2 25d ago A 9 tokens copy · 100% MIT

web-researcher

21

shahidshabbir-se/my-pi-setup

Agent Claude Code

Research current external information, official library/API documentation, and comparisons. Verify claims against primary sources and return findings with source URLs and limitations.

not rated 2 2d ago A 32 tokens original MIT

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: