82 tagged agent-pipeline, measured the same way as everything else here.
Browse within: Multi-Agent 10agent-framework 10llm-tools 10
Skill Claude CodeCodex
Skill "skills" from david-spies/ai-agent-builder, covering skillauthoring.md — complete guide to writing agent skills, ai-agent builder · documentation, the skill.md standard, anatomy of a skill.md file and full skill.md template.
Instructions file CodexOpenCode
AGENTS.md instructions for david-spies/ai-agent-builder, covering agents.md — city map, ai-agent builder · orchestration configuration, agentskills.io standard · v1.0.0, project structure — the city map and agent roles.
Skill Claude CodeCodex
Builds, configures, validates, and packages production-ready AI agents. Generates complete SKILL.md, AGENTS.md, guardrails, llm-judge, audit-trail, governance, and permissions configuration files following the agentskills.io open standard. Activates when a user wants to create, design, scaffold, or deploy an AI agent…
Agent Claude Code
Final review of the diff for correctness, security, conventions, and spec conformance. Waits for CI green. On clean verdict, appends one line to LEARNINGS.md and signals merge-ready. On blocking findings, emits HANDOFF:FIX to coder. Read-only on source code.
Command Claude Code
Run the full delivery pipeline (planner → red-team → coder → smoke-tester → reviewer) against a GitHub issue. Bridges Claude Code's missing auto-handoff button by invoking each subagent in sequence via the Agent tool, validating typed HANDOFF blocks, breaking on repeat failures, and logging every stage to…
Settings file Claude Code
Agent settings declaring 8 allowed tools.
Cursor rule Cursor
How to use bastion subagents, HANDOFF blocks, and gh CLI in Agent mode.
Skill Claude CodeCodexCursor
Creates and structures GitHub issues and labels using gh CLI conventions. Use when creating or editing GitHub issues, triaging, defining label taxonomy, or running gh issue or gh label commands. Use when the user asks to create issues, plan a feature with issues, break down work into GitHub tasks, or set up labels and…
Agent
Read-only reviewer. Reads the PR diff, identifies issues, and hands off to IssueCoder to fix them. Never writes code.
Agent
Run smoke tests after implementation — build, unit tests, start server if applicable, curl live endpoints, report results.
MCP server Claude CodeCodexCursor +2
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Instructions file CodexOpenCode
Instructions for JoakimCarlsson/bastion, covering agents.md — bastion contributor and agent contract, project summary, hard rules — verification (non-negotiable), smoke example and or: docker compose up --build.
Settings file Claude Code
Agent settings configuring permissions.
Skill Claude CodeCodex
Build, inspect, verify, and maintain PipeBuilder PipeSpaces and PipeBuilder-managed Agent Skills. Use when creating or editing a Skill, changing pipespace.json, resolving Skill Providers or generated-artifact drift, running PipeBuilder commands, or updating the installed PipeBuilder CLI.
Agent
Golden CodeBuddy reviewer.
Command Cursor
GOLDENCURSORSKILLCOMMAND.
MCP server Claude CodeCodexCursor +2
MCP server "hbfixture" as configured in agentpipe/pipebuilder. Runs pass with python3.
Command
GOLDENCODEBUDDYSPACECOMMAND.
Cursor rule Cursor
Golden Cursor space rule.
Cursor rule Cursor
Require evidence-backed bug diagnosis and regression checks.
Skill Claude CodeCodex
Diagnose a reported defect, verify its cause, and review the proposed fix.
Cursor rule Cursor
Apply focused implementation and verification guidance.
Skill Claude CodeCodex
Implement and verify a product feature in the referenced project.
Skill Claude CodeCodex
Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "/15 "), records the schedule, and acknowledges back to the user.
At most 3 mods per repository are shown here — the rest are on their repository pages: