Is the Agent Loop skill free?

Yes. The skill itself is free from vinnie357/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Loop SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Agent Loop?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Loop with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Loop

Multi-agent epic-to-PR workflow: 4-phase execution, tiered models, TDD gates

by vinnie357 · vinnie357/claude-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8f3b31a

The skill's own text admits its cross-plugin '/claude-code:*' loads won't resolve standalone, but understates the bigger problem: the standard single-folder install (cp -r .../agent-loop) also drops all nine 'mandatory' same-plugin skills it Skill-loads by name (/core:tdd, /core:restraint, /core:bees, /core:git, /core:mise, /core:nushell, /core:security, /core:twelve-factor, /core:anti-fabrication) — none of which exist after that copy.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Agent Loop does

Defines a 4-phase, 6-tier multi-agent workflow (codename Forge) for taking an epic or issue through decomposition, paired-team implementation, CI validation, and PR submission with per-tier model assignment. Triggers on epic/issue work phrasing ('work epic <id>', 'forge <id>') and, per its own description, on casual feature requests generally. Depends on nine sibling '/core:*' skills and an optional '/claude-code:*' plugin that are not included when only this skill folder is installed.

How to install Agent Loop

git clone https://github.com/vinnie357/claude-skills
cd claude-skills
mkdir -p ~/.claude/skills
cp -r plugins/core/skills/agent-loop ~/.claude/skills/agent-loop

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Loop

/agent-loop Multi-agent epic-to-PR workflow: 4-phase execution, tiered models, TDD gates

It also activates on plain-language prompts like these:

Work this epic through decomposition to a finished pull request
Break this issue into a paired implementation and CI plan
Hand this feature off to a tiered team of coding agents

Frequently asked questions

Is the Agent Loop skill free?: Yes. The skill itself is free from vinnie357/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Loop work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. The skill's own text admits its cross-plugin '/claude-code:*' loads won't resolve standalone, but understates the bigger problem: the standard single-folder install (cp -r .../agent-loop) also drops all nine 'mandatory' same-plugin skills it Skill-loads by name (/core:tdd, /core:restraint, /core:bees, /core:git, /core:mise, /core:nushell, /core:security, /core:twelve-factor, /core:anti-fabrication) — none of which exist after that copy.
What is the Agent Loop SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Agent Loop?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Loop with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.