coding agent agents

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.

bgrenat/godot-game-dev-studio

Agent Claude Code

Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.

bunhine0452/Ocul-PM

Agent

An agent instruction template for recording completed work in an ocul-pm tracking project. It covers work such as bug fixes, features, refactoring, error investigations, and routine changes.

bunhine0452/Ocul-PM

Agent

A discussion-document format for recording a problem and comparing possible solutions before making a decision. It belongs to ocul-pm, a project-management system that keeps work notes and plans in files.

curtischoutw/claude-institution

Agent

A review agent that examines code or designs for security risks and ways they may fail. It checks inputs, permissions, secrets, concurrent operations, partial failures, and injection attacks, where untrusted data changes a command or query.

curtischoutw/claude-institution

Agent

A review agent that looks for unnecessary complexity in code or software designs. It proposes a concrete simpler replacement when it finds overengineering.

curtischoutw/claude-institution

Agent

A review agent that tries to disprove a claim, conclusion, or code change. It checks assumptions, uses repository tools and commands, and reports whether the claim survived its scrutiny.

TheStreamCode/super-cli

Agent

These compact marks identify compatible third-party CLIs. They do not make Super CLI an official client, partner, or endorsed product. Vendor marks remain the property of their respective owners and are excluded from Super CLI's MIT license; see TRADEMARKS.md.

zebbern/termstack

Agent

Quality-first workflow coordinator. Clarifies intent, researches current guidance, uses discordask, discordembed, and discordnotify for user communication, and delegates the full lifecycle to subagents.

zebbern/termstack

Agent

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.

zebbern/termstack

Agent

Anti-laziness task implementer. Implements one task at a time with full specification adherence and DO NOT/MUST enforcement. Returns per-criterion confirmation.

alexei-led/resume-from

Agent

The Claude Code plugin adds /resume-from and includes the matching command binary.

alexei-led/resume-from

Agent

The Codex plugin adds a /resume-from prompt. The prompt runs the matching published command package.

alexei-led/resume-from

Agent

Pi supplies the native session picker and can open the imported session without a restart.

evoelsewhere/evoflux

Agent

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

evoelsewhere/evoflux

Agent

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

evoelsewhere/evoflux

Agent

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

jyjeanne/rustyspec

Agent

Execute tasks from the task breakdown.

jyjeanne/rustyspec

Agent

Generate an architecture plan from a specification.

jyjeanne/rustyspec

Agent

Create a new feature specification.

LeanAndMean/scramjet

Agent

Verifies that a pull request fully implements the requirements from its linked issue and implementation plan, identifying missing or partially implemented features.

LeanAndMean/scramjet

Agent

Designs test strategies from requirements and architecture, providing per-test cost/benefit assessments, coverage intent categorization, and test-first recommendations for bug fixes.

LeanAndMean/scramjet

Agent

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

CercaTrovato/agent-rongchi

Agent

Claude Code, claude.ai, and the Claude Agent SDK all read ../SKILL.md directly. Unlike OpenAI (see openai.yaml), Claude needs no separate manifest — the YAML frontmatter in SKILL.md (name + description) is the whole contract.