How do I install the Forge Plan skill?

Run npx skillmds@latest add redteamlife/forge-plan in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Forge Plan safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Forge Plan?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Forge Plan free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Forge Plan?

redteamlife (@redteamlife) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Forge Plan by redteamlife — Agent Skill

Name: Forge Plan
Author: redteamlife

Forge Plan

Use when the user asks to plan, break down, sequence, or add tasks in a repo containing `docs/forge/` or governed by FORGE. Shapes bounded tasks (scope, file_scope, dependencies, review needs) in the configured task source without implementing.

redteamlife 96e05c3 1.4 KB Updated Sep 17, 2026

File contents

FORGE Plan

Use this skill when the user asks to plan, break down, sequence, or prepare FORGE-governed work.

Workflow

Read docs/forge/CONTEXT.md if present, then docs/forge/AI.md if present.
Identify the authoritative task source: local TASKS.index.yaml plus task files, legacy TASKS.yaml, GitHub Issues, GitLab Issues, or external tracker.
Use ../references/lifecycle-map.md only when lifecycle routing is ambiguous.
Shape tasks with bounded scope, file scope, dependencies, contract files, and review requirements.
For design/architecture work, record a task_type: design task whose document lives under docs/forge/designs/. Design tasks are tracked by review_state (draft|in-review|changes-requested|accepted) and are exempt from execution gates — do not attach a gates: block to them.
Do not implement unless the user explicitly switches to build or forge-execute-task.

Hard Stops

Stop when the authoritative task source is unclear, a task cannot be bounded, or a contract/architecture decision is needed before sequencing.

Evidence Required

task entries, issue links, or explicit human-approved task breakdown

Frequently asked questions