task-setup

task-setup is a skill for Claude Code, Codex from mandrianova/jb-task-manager-extension. It costs 25 tokens per session (888 once invoked), scanned A, original, MIT.

A setup skill for initializing the Task Manager files in a project. It creates the task directory and task data file when needed, installs the task command-line tool, and can configure local permissions for Claude Code.

In plain words
What is it for?
Use it when first enabling task management in a project or when the project's task files and command-line helper are missing.
Why use it?
It removes the manual setup needed before a project can store and manage tasks with the Task Manager.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is "Bash(bash .claude/tasks/task-cli.sh:*)",.

Good fit Use it when first enabling task management in a project or when the project's task files and command-line helper are missing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mandrianova/jb-task-manager-extension
agentmods
npx agentmods add skills/mandrianova/jb-task-manager-extension/task-setup

Made for: Claude Code, Codex.

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 task-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/mandrianova/jb-task-manager-extension/task-setup/github.svg)](https://agentmods.dev/skills/mandrianova/jb-task-manager-extension/task-setup)
Your own site
<a href="https://agentmods.dev/skills/mandrianova/jb-task-manager-extension/task-setup"><img src="https://agentmods.dev/badge/skills/mandrianova/jb-task-manager-extension/task-setup/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 task-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/mandrianova/jb-task-manager-extension/task-setup"><img src="https://agentmods.dev/badge/skills/mandrianova/jb-task-manager-extension/task-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 888 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 $0.00025 $0.00888
Opus 5.5 $0.00010 $0.00355
Sonnet 5.5 $0.00005 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 1mo ago against content hash bc1ba78cd0a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-setup 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 1mo 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.

skills/task-setup/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Setup

Configure the current project for the Task Manager plugin and agent skills.

What this does

  1. Resolves the task directory and creates it with tasks.json if missing
  2. Copies task-cli.sh if missing
  3. For Claude Code, creates or updates .claude/settings.local.json with permissions for task management paths

Steps

1. Resolve and initialize task directory

Resolve TASKS_DIR:

  1. If TASK_MANAGER_TASKS_DIR is set, use that.
  2. Else if .claude/tasks exists, use .claude/tasks for backward compatibility.
  3. Else if .agents/tasks exists, use .agents/tasks.
  4. Else if .kiro/tasks exists, use .kiro/tasks.
  5. Else if .idea/agents-tasks exists, use .idea/agents-tasks.
  6. Else if TASK_MANAGER_AGENT=codex or you are running in Codex, use .agents/tasks; if TASK_MANAGER_AGENT=kiro-cli or you are running in Kiro, use .kiro/tasks; otherwise use .claude/tasks.
mkdir -p "$TASKS_DIR/docs"

If $TASKS_DIR/tasks.json doesn't exist, create it:

{"groups": []}

2. Install task-cli.sh

If $TASKS_DIR/task-cli.sh doesn't exist, check if it's available at:

  • scripts/task-cli.sh (in current project, if this is the plugin repo)
  • The global skills directory

If found, copy it and make executable. If not found, inform the user they need to install the Task Manager plugin skills first.

3. Configure Claude permissions when applicable

If you are running in Claude Code, read .claude/settings.local.json if it exists. Merge the following permissions into the existing allow array (don't replace existing rules):

{
  "permissions": {
    "allow": [
      "Bash(bash .claude/tasks/task-cli.sh:*)",
      "Bash(bash .agents/tasks/task-cli.sh:*)",
      "Bash(bash .kiro/tasks/task-cli.sh:*)",
      "Bash(bash .idea/agents-tasks/task-cli.sh:*)",
      "Bash(git log:*)",
      "Bash(git rev-parse:*)",
      "Bash(git add:*)",
      "Bash(git commit:*)",
      "Bash(git diff:*)",
      "Bash(git status:*)",
      "Read(.claude/tasks/**)",
      "Edit(.claude/tasks/**)",
      "Write(.claude/tasks/**)",
      "Read(.agents/tasks/**)",
      "Edit(.agents/tasks/**)",
      "Write(.agents/tasks/**)",
      "Read(.kiro/tasks/**)",
      "Edit(.kiro/tasks/**)",
      "Write(.kiro/tasks/**)",
      "Read(.idea/agents-tasks/**)",
      "Edit(.idea/agents-tasks/**)",
      "Write(.idea/agents-tasks/**)"
    ]
  }
}

Read the full file on GitHub · 105 lines

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. 1mo ago First seen · 105 lines · 25 tokens per session scan A bc1ba78cd0a4

Subscribe to this mod's changes

task-setup is a skill published in the GitHub repository mandrianova/jb-task-manager-extension (4 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 888 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories