role-task

role-task is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 196 tokens per session (656 once invoked), scanned A, original, MIT.

A session role that assigns the coding and build responsibilities for implementing approved work items, including commits and pushes when permitted.

In plain words
What is it for?
Use it when this session should build items from the project’s designated work queue and handle the related version-control steps.
Why use it?
It clarifies who owns implementation and repository delivery work during a multi-agent development process.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it when this session should build items from the project’s designated work queue and handle the related version-control steps.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for role-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/role-task/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/role-task)
Your own site
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/role-task"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/role-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for role-task

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/role-task"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/role-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00196 $0.00656
Opus 5 $0.00098 $0.00328
Sonnet 5 $0.00039 $0.00131
Haiku 4.5 $0.00020 $0.00066

Measured 11d ago against content hash 8ac459fc49ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

role-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/credo/skills/role-task/SKILL.md · 55 lines

What it actually says

Session Role: task / build

Set this session's credo ROLE to task / build. This is a guiding default owner of implementing GO items (items in 2_go/), INCLUDING commits and push where dogma permissions allow. Only the task/build role commits and pushes, 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-task (the explicit, deterministic, guaranteed path).
  • The user assigns you this role in passing (best-effort, casual path) - for example "you are now the task/build agent", "you build the GO items", "take over the implementing", "act as the build agent", "du baust die GO-items", "uebernimm das Bauen".

Do NOT trigger on general discussion about roles, on explanations, or on questions such as "what does the task 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" task

Confirm

Confirm in one short sentence, for example:

Role set to task/build - I am the default owner of building GO items (items in 2_go/), including commits and push where dogma permits. 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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 55 lines · 196 tokens per session scan A 8ac459fc49ff

Subscribe to this mod's changes

role-task is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 196 tokens to every session and 656 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.