AgentBuildersApp

21 mods across 1 repository, 2 stars between them.

8eyes

02

AgentBuildersApp/eight-eyes

Plugin Claude Code

Failure-aware multi-agent code review with 8 hook-enforced roles. Works on Claude Code, Copilot CLI, and Codex CLI.

2 29d ago A tokens not measured original MIT

AgentBuildersApp/eight-eyes

Agent

Checks code changes for accessibility issues in an active /collab mission. Use when changes touch UI components or a11ycommands are configured.

2 29d ago A 33 tokens original MIT

collab-docs

04

AgentBuildersApp/eight-eyes

Agent

Updates documentation for verified changes in an active /collab mission. Use when the mission has passed verification and documentation needs updating.

2 29d ago A 30 tokens original MIT

collab-implementer

05

AgentBuildersApp/eight-eyes

Agent

Implements code changes for an active /collab mission. Use when the mission is in implement phase and actual file edits are required.

2 29d ago A 33 tokens original MIT

collab-performance

06

AgentBuildersApp/eight-eyes

Agent

Profiles code changes for performance issues in an active /collab mission. Use when changes touch hot paths, queries, or benchmarkcommands are configured.

2 29d ago A 33 tokens original MIT

collab-security

07

AgentBuildersApp/eight-eyes

Agent

Audits code changes for security vulnerabilities in an active /collab mission. Use when the mission touches auth, crypto, user input, or has securityscancommands configured.

2 29d ago A 38 tokens original MIT

collab-skeptic

08

AgentBuildersApp/eight-eyes

Agent

Performs a blind review of an active /collab mission. Use when the mission is in review phase and you need an independent, risk-focused critique.

2 29d ago A 37 tokens original MIT

collab-test-writer

09

AgentBuildersApp/eight-eyes

Agent

Writes tests for code changes in an active /collab mission. Use when the mission is in test phase and tests need to be created for the implementer's changes.

2 29d ago A 39 tokens original MIT

collab-verifier

10

AgentBuildersApp/eight-eyes

Agent

Verifies an active /collab mission against acceptance criteria and approved test commands. Use when the mission is in verify phase.

2 29d ago A 30 tokens original MIT

8eyes

11

AgentBuildersApp/eight-eyes

Skill Claude CodeCodex

Multi-agent adversarial code review via eight-eyes enforcement kernel.

2 29d ago A 15 tokens original MIT

SessionStart

14

AgentBuildersApp/eight-eyes

Hook

Runs when a session starts on startup, resume, clear and compact, executing collab_session_start.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

PreToolUse

15

AgentBuildersApp/eight-eyes

Hook

Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing collab_pre_tool.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

PostToolUse

16

AgentBuildersApp/eight-eyes

Hook

Runs after a tool call finishes for Write, Edit, MultiEdit and Bash tool calls, executing collab_post_tool.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

SubagentStart

17

AgentBuildersApp/eight-eyes

Hook

Runs when a subagent starts for collab- tool calls, executing collab_subagent_start.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

SubagentStop

18

AgentBuildersApp/eight-eyes

Hook

Runs when a subagent finishes for collab- tool calls, executing collab_subagent_stop.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

PreCompact

19

AgentBuildersApp/eight-eyes

Hook

Runs before the context is compacted, executing collab_pre_compact.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured copy · 86% MIT

Stop

20

AgentBuildersApp/eight-eyes

Hook

Runs when the agent finishes a response, executing collab_stop.py via python3. From AgentBuildersApp/eight-eyes.

2 29d ago A tokens not measured original MIT

collab

21

AgentBuildersApp/eight-eyes

Skill Claude CodeCodex

Failure-aware multi-agent mission coordinator. Activate when the user invokes /collab or explicitly requests a multi-agent review, implementation, or audit mission.

2 29d ago A 36 tokens original MIT