How do I install the Role Plan skill?

Run npx skillmds@latest add marcel-bich/role-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 Role 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 Role 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 Role Plan free to use?

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

Who published Role Plan?

Marcel-Bich (@marcel-bich) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Role Plan by marcel-bich — Agent Skill

Name: Role Plan
Author: Marcel-Bich

Role Plan

Assign this session the credo plan/clarify role - the default owner of clarifying items in 1_clarify/, WITHOUT commits or push (the task/build role owns commits and push). Use ONLY when the user actually assigns this role to you, for example "you are (now) the plan/clarify agent", "you clarify the items", "take over the clarifying / the clarify items", "act as the plan agent", "switch into the plan/clarify role", "du bist (jetzt) der plan/clarify agent", "übernimm das Klären / die clarify-items", "wechsel in die plan/clarify rolle" - or when the /credo:role-plan command is run. Do NOT use for general talk ABOUT roles, explanations, or questions like "what does the plan agent do". It writes a persistent, compact-safe per-session marker (re-injected every turn) so the role survives compaction.

Marcel-Bich be900b5 2.9 KB Updated Sep 17, 2026

File contents

Session Role: plan / clarify

Set this session's credo ROLE to plan / clarify. This is a guiding default owner of clarifying items in 1_clarify/, WITHOUT commits or push. Committing and pushing are the task/build role's job, so a single index owner avoids a race on .git/index.lock.

A role is orthogonal to the session mode (active | passive | autonomous): it can coexist with any mode. It is a guiding default, NOT a fixed constraint - on the user's wish you may still do mixed work, and an explicit user instruction always overrides the role.

When to use

The user runs /credo:role-plan (the explicit, deterministic, guaranteed path).
The user assigns you this role in passing (best-effort, casual path) - for example "you are now the plan/clarify agent", "you clarify the items", "take over the clarifying", "act as the plan agent", "uebernimm das Klaeren", "du bist der plan/clarify agent".

Do NOT trigger on general discussion about roles, on explanations, or on questions such as "what does the plan agent do" - those are not an assignment.

What it does

Write the persistent, per-session role marker. It is keyed by session_id under the session-roles dir and re-injected on every prompt by role-inject.sh, so it survives context compaction, new sessions and subagents (stored on disk, not in context):

"${CLAUDE_PLUGIN_ROOT}/hooks/role-set.sh" plan

Sandbox pre-work

For WRITING clarify pre-work that needs no product decision but evidence - a measurement, a mockup, a feasibility proof - use the sandbox skill. It builds under .credo/sandbox-tmp/ (no production code, no commit); an accepted artifact is promoted via /credo:sandbox-promote, which the task / build role commits.

Confirm

Confirm in one short sentence, for example:

Role set to plan/clarify - I am the default owner of clarifying items in 1_clarify/, without commits or push (the task/build role owns those). This is persistent and compact-safe (re-injected each turn); it is a guiding default you can override, and /credo:role-clear removes it.

Do not do anything else - this skill only sets the role.

---name: role-plandescription: Assign this session the credo plan/clarify role - the default owner of clarifying items in 1_clarify/, WITHOUT commits or push (the task/build role owns commits and push). Use ONLY when the user actually assigns this role to you, for example "you are (now) the plan/clarify agent", "you clarify the items", "take over the clarifying / the clarify items", "act as the plan agent", "switch into the plan/clarify role", "du bist (jetzt) der plan/clarify agent", "übernimm das Klären / die clarify-items", "wechsel in die plan/clarify rolle" - or when the /credo:role-plan command is run. Do NOT use for general talk ABOUT roles, explanations, or questions like "what does the plan agent do". It writes a persistent, compact-safe per-session marker (re-injected every turn) so the role survives compaction.---# Session Role: plan / clarifySet this session's credo ROLE to **plan / clarify**. This is a guiding default owner ofclarifying items in `1_clarify/`, WITHOUT commits or push. Committing and pushing are thetask/build role's job, so a single index owner avoids a race on `.git/index.lock`.A role is orthogonal to the session mode (active | passive | autonomous): it can coexist withany mode. It is a guiding default, NOT a fixed constraint - on the user's wish you may still domixed work, and an explicit user instruction always overrides the role.## When to use- The user runs `/credo:role-plan` (the explicit, deterministic, guaranteed path).- The user assigns you this role in passing (best-effort, casual path) - for example "you are now the plan/clarify agent", "you clarify the items", "take over the clarifying", "act as the plan agent", "uebernimm das Klaeren", "du bist der plan/clarify agent".Do NOT trigger on general discussion about roles, on explanations, or on questions such as"what does the plan agent do" - those are not an assignment.## What it doesWrite the persistent, per-session role marker. It is keyed by session_id under thesession-roles dir and re-injected on every prompt by `role-inject.sh`, so it survives contextcompaction, new sessions and subagents (stored on disk, not in context):```bash"${CLAUDE_PLUGIN_ROOT}/hooks/role-set.sh" plan```## Sandbox pre-workFor WRITING clarify pre-work that needs no product decision but evidence - a measurement, amockup, a feasibility proof - use the `sandbox` skill. It builds under `.credo/sandbox-tmp/`(no production code, no commit); an accepted artifact is promoted via `/credo:sandbox-promote`,which the task / build role commits.## ConfirmConfirm in one short sentence, for example:> Role set to plan/clarify - I am the default owner of clarifying items in `1_clarify/`, without> commits or push (the task/build role owns those). This is persistent and compact-safe (re-injected> each turn); it is a guiding default you can override, and `/credo:role-clear` removes it.Do not do anything else - this skill only sets the role.

Frequently asked questions