task-manager

task-manager is a skill for Claude Code from zeenie-ai/OpenCompany. It costs 29 tokens per session (1,229 once invoked), scanned A, original, MIT.

A durable task-management system for assigning work to connected teammates and reviewing what they return.

In plain words
What is it for?
Splitting independent work into missions, assigning them to teammates, checking task traces, and accepting or retrying results.
Why use it?
It helps prevent duplicate assignments and keeps task outcomes, retries, reassignment, and cancellation recorded in one workflow.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Splitting independent work into missions, assigning them to teammates, checking task traces, and accepting or retrying results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zeenie-ai/opencompany/task-manager
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.

Any agent
npx skills add zeenie-ai/OpenCompany --skill task-manager
Clone the repo
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany

Made for: Claude Code.

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/zeenie-ai/opencompany/task-manager/github.svg)](https://agentmods.dev/skills/zeenie-ai/opencompany/task-manager)
Your own site
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/task-manager"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/task-manager/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-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/task-manager"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/task-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,229 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00029 $0.01229
Opus 5 $0.00015 $0.00615
Sonnet 5 $0.00006 $0.00246
Haiku 4.5 $0.00003 $0.00123

Measured 10d ago against content hash d5cc073ef314, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

server/skills/assistant/task-manager/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Manager

Use task_manager as the team lead's durable control plane. It is scoped to the current workflow execution and only permits assignment to agents connected to this lead's input-teammates handle.

Required workflow

  1. Call list_tasks with include_history=true before assigning work so you do not duplicate a mission from an earlier workflow execution.
  2. Split independent work into bounded tasks with explicit acceptance criteria.
  3. Call assign_task once per mission. Use the connected teammate node ID or the exact delegate name reported by the lead's available teammate list. Do not call delegate_to_* directly; delegate descriptors are internal dispatch identities, not the lead's task-creation interface.
  4. Independent tasks may be assigned together. The durable queue starts at most three descendants across the whole agent tree; excess tasks remain queued. After assign_task returns queued, report that delegation started and return immediately. Do not poll or wait in the assigning invocation.
  5. When a teammate submits work or an attempt fails, call get_task, then use inspect_task_trace before retrying, reassigning, or reporting a terminal failure. Start with detail="summary"; use failures or a paginated timeline only when the summary does not explain the outcome. For large histories use detail="search" with a narrow query, inspect the returned context lines, and follow next_cursor until the match is found or the cursor is empty. Prefer categories and all_terms over broad searches. Copy task.id to task_id and task.revision to expected_revision for the review mutation.
  6. Choose exactly one review outcome:
    • accept_task when the result satisfies the task;
    • modify_task for blocked or queued work;
    • retry_task when the mission is still valid;
    • reassign_task to another connected teammate with revision context;
    • cancel_task when the work is no longer needed.
  7. Call finish_team only after every required task is accepted or intentionally cancelled. Synthesize accepted results in the final report and disclose any unresolved failure.

Read the full file on GitHub · 100 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. 10d ago First seen · 100 lines · 29 tokens per session scan A d5cc073ef314

Subscribe to this mod's changes

task-manager is a skill published in the GitHub repository zeenie-ai/OpenCompany (878 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,229 once invoked, about $0.0001 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.