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.
npx agentmods add skills/ericroliver/tinytask/skillnpx skills add ericroliver/tinytask --skill skillgit clone --depth 1 https://github.com/ericroliver/tinytaskWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.04081 |
| Opus 5 | $0.00010 | $0.02041 |
| Sonnet 5 | $0.00004 | $0.00816 |
| Haiku 4.5 | $0.00002 | $0.00408 |
Grade A, and why
task-management 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent names (e.g.,
tko-sword,tko-shield) are examples. Use actual names from your environment — defined in yourAGENTS.mdfile. Replace placeholders like<your-agent>,<qa-agent>,<developer>with real names.
TinyTask Shared Skill
Overview
TinyTask is a task management system for LLM agent collaboration, exposed as an MCP server, HTTP API, and CLI. The tinytask CLI communicates with the server over HTTP. Role-specific workflows live in developer.md, tester.md, reviewer.md, and coordinator.md — this file is the CLI syntax and conventions reference.
Core Concepts
| Concept | Description |
|---|---|
| Task | Fundamental unit of work — has title, description, status, assignee, queue, priority, tags, optional parent and blocked-by |
| Subtask | Task with parent_task_id set — full task with own lifecycle; does not auto-change parent status |
| Queue | Named collection of tasks — routing mechanism determining which agent picks up work |
| Comment | Annotation attached to a task — primary inter-agent communication channel |
| Link | Typed URL-based relationship between tasks or external resources (PRs, docs) |
| History | Immutable log of every task change (status, queue, assignee, fields) with timestamp and agent |
Task Fields
| Field | Type | Required | Description |
|---|---|---|---|
id |
string (auto) | Yes | Unique ID (YYYYMMDD_NN) |
title |
string | Yes | Short summary, <80 chars, action verb prefix |
description |
string | Yes | What, why, acceptance criteria |
status |
enum | Yes | idle | working | complete |
assigned_to |
string | No | Agent responsible for the task |
created_by |
string | Yes | Agent that created the task |
priority |
enum | No | low | medium | high | urgent (default: medium) |
tags |
JSON array | No | Lowercase, hyphenated labels |
queue_name |
string | No | Queue the task belongs to |
parent_task_id |
string | No | Parent task if subtask |
blocked_by_task_id |
string | No | Task ID that blocks this task |
created_at |
ISO 8601 | Yes | Creation timestamp |
updated_at |
ISO 8601 | Yes | Last modification time |
completed_at |
ISO 8601 | No | When marked complete (nullable) |
archived_at |
ISO 8601 | No | When archived (nullable) |
What ships with it
6 files 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.
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.
- yesterday First seen · 315 lines · 21 tokens per session scan A 0a713d8d285e
task-management is a skill published in the GitHub repository ericroliver/tinytask (1 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 4,081 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…