task-manager

task-manager is a skill for Claude Code, Codex from iamlukethedev/Hermes3D. It costs 56 tokens per session (1,403 once invoked), scanned A, original, MIT.

A task-management skill that records user requests as persistent tasks and keeps their status updated on a shared Kanban board. A Kanban board is a visual list of work waiting, in progress, blocked, or complete.

In plain words
What is it for?
Creating tasks, moving them through statuses, marking work blocked or complete, and checking the current task list.
Why use it?
It prevents actionable requests and their progress from being lost in conversation history. The shared task file gives the board one consistent source of truth.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/iamlukethedev/hermes3d/task-manager
Any agent
npx skills add iamlukethedev/Hermes3D --skill task-manager
Clone the repo
git clone --depth 1 https://github.com/iamlukethedev/Hermes3D

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamlukethedev/hermes3d/task-manager.svg)](https://agentmods.dev/skills/iamlukethedev/hermes3d/task-manager)
Your own site
<a href="https://agentmods.dev/skills/iamlukethedev/hermes3d/task-manager"><img src="https://agentmods.dev/badge/skills/iamlukethedev/hermes3d/task-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.01403
Opus 5 $0.00028 $0.00701
Sonnet 5 $0.00011 $0.00281
Haiku 4.5 $0.00006 $0.00140

Measured 4d ago against content hash ae2da229c291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-manager 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 4d 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.

assets/skills/task-manager/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Manager

Use this skill for task capture and task lifecycle updates.

Trigger

{
  "activation": {
    "anyPhrases": [
      "add a task",
      "create a task",
      "track this task",
      "task status",
      "mark this done",
      "block this task",
      "what tasks do we have"
    ]
  },
  "movement": {
    "target": "desk",
    "skipIfAlreadyThere": true
  }
}

Also use this skill even when those exact phrases are absent if the latest user message is an actionable work request. If the user asks the agent to do something, that request must become a task before the agent proceeds.

Storage location

The authoritative task file is:

  • ${HERMES_STATE_DIR}/hermes3d/task-manager/tasks.json when HERMES_STATE_DIR is set.
  • ~/.hermes/hermes3d/task-manager/tasks.json otherwise.

Always treat that file as the shared source of truth for the Kanban board.

Required workflow

  1. Read the task file before handling an actionable request.
  2. If the file does not exist, create it with the schema in this document.
  3. If the latest user message is actionable and no matching active task exists, create one immediately.
  4. Before starting execution, move the task from inbox to working.
  5. If work is blocked on a human (command approval, missing input, credentials, or an error), set the task to needs_attention and record a short reason in notes.
  6. When work is finished, set the task to done.
  7. When a task is queued by the cron scheduler or a playbook for a later run, keep it in scheduled and set scheduledFor.
  8. After every mutation, write the full updated JSON back to disk.

Matching rules

  • Match first by externalThreadId when the request comes from a stable thread or conversation.
  • Otherwise match by a concise normalized title that preserves user intent.
  • Avoid creating duplicate active tasks for the same request.

Task fields

Each task must include:

  • id
  • title
  • description
  • status
  • source
  • sourceEventId
  • assignedAgentId
  • createdAt
  • updatedAt
  • playbookJobId
  • runId
  • channel
  • externalThreadId
  • lastActivityAt
  • notes
  • isArchived
  • isInferred
  • model
  • skills
  • subagentCount
  • scheduledFor
  • learnedSkill
  • history

Read the full file on GitHub · 165 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 165 lines · 56 tokens per session scan A ae2da229c291

Subscribe to this mod's changes

task-manager is a skill published in the GitHub repository iamlukethedev/Hermes3D (337 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,403 once invoked, about $0.0003 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.