What is todo-for-ai-agent-runtime?

A runtime connection for an external software agent to receive tasks from Todo for AI and report progress through its HTTP API.

It helps an agent authenticate, pull and renew tasks, send events and logs, and commit final results.

It defines the sign-in, task ownership, and result-reporting steps an agent needs to work safely without losing track of assigned tasks.

todo-for-ai-agent-runtime — Skill for Claude Code and Codex by todo-fo

About the project

Todo for AI is a task management system designed for AI assistants, with support for projects, tasks, team collaboration, and the Model Context Protocol (MCP), which lets compatible assistants interact with external tools. It is for teams and individuals coordinating work between AI agents and people. Its catalogue entry provides an instruction and a skill for using the system.

todo-for-ai/todo-for-ai · 1,180 stars · on GitHub · todo4ai.org

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 todo-for-ai/todo-for-ai --skill agent_runtime

Clone the repo

git clone --depth 1 https://github.com/todo-for-ai/todo-for-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/todo-for-ai/todo-for-ai/agent_runtime/github.svg)](https://agentmods.dev/skills/todo-for-ai/todo-for-ai/agent_runtime)

Your own site

<a href="https://agentmods.dev/skills/todo-for-ai/todo-for-ai/agent_runtime"><img src="https://agentmods.dev/badge/skills/todo-for-ai/todo-for-ai/agent_runtime/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/todo-for-ai/todo-for-ai/agent_runtime"><img src="https://agentmods.dev/badge/skills/todo-for-ai/todo-for-ai/agent_runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,570 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.01570
Opus 5	$0.00019	$0.00785
Sonnet 5	$0.00008	$0.00314
Haiku 4.5	$0.00004	$0.00157

Measured 5d ago against content hash 2825b2d6fdff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

todo-for-ai-agent-runtime 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 5d 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.

docs/AGENT_RUNTIME_SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Todo for AI Agent Runtime Skill

1. Goal

You are an execution agent connected to Todo for AI. Your job is to pull tasks, execute safely, and report progress and final status using the platform protocol.

2. Required Inputs

API_BASE_URL (example: https://api.todo-for-ai.com/todo-for-ai/api/v1)
AGENT_KEY (long-lived key, prefix agk_)

3. Auth Flow

Exchange AGENT_KEY for short-lived access token.
Use returned token in Authorization: Bearer <access_token>.
Refresh token when expired.

3.1 Token Exchange

POST /agent/auth/introspect

Request JSON:

{
  "agent_key": "agk_xxx"
}

Success response includes:

access_token
expires_in
agent.id
agent.workspace_id

4. Pull + Lease Protocol

4.1 Pull Task

POST /agent/tasks/pull

Optional body:

{
  "max_tasks": 1
}

Each item returns:

task_id
attempt_id
lease_id
lease_expires_at
payload (title/content/tags/priority)

4.2 Renew Lease

Before lease expiry, renew periodically.

POST /agent/tasks/{task_id}/lease/renew

{
  "attempt_id": "att_xxx",
  "lease_id": "lea_xxx"
}

If LEASE_EXPIRED or LEASE_NOT_OWNER, stop writing results for this attempt.

5. Progress/Event Reporting

POST /agent/tasks/{task_id}/events

{
  "attempt_id": "att_xxx",
  "events": [
    {
      "type": "progress",
      "seq": 1,
      "timestamp": "2026-03-05T00:00:00Z",
      "message": "Started execution",
      "payload": {"percent": 10}
    }
  ]
}

6. Task Log Append (Recommended)

Use logs for human-readable execution trace.

6.1 Append Log

POST /agent/tasks/{task_id}/logs

{
  "content": "Analyzed requirement and generated implementation plan.",
  "content_type": "text/markdown"
}

6.2 Read Existing Logs

GET /agent/tasks/{task_id}/logs

7. Final Commit (Idempotent)

POST /agent/tasks/{task_id}/commit

Headers:

Idempotency-Key: <stable-unique-key>

Body:

{
  "attempt_id": "att_xxx",
  "lease_id": "lea_xxx",
  "status": "succeeded"
}

Read the full file on GitHub · 268 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.

5d ago First seen · 268 lines · 39 tokens per session scan A 2825b2d6fdff

Subscribe to this mod's changes

todo-for-ai-agent-runtime is a skill published in the GitHub repository todo-for-ai/todo-for-ai (1,180 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,570 once invoked, about $0.0002 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 2026-09-03.

Building agents Project management ai-coding-tools cursor kiro todo4ai trae windsurf

progress-tracker

Progress Tracker skill - Monitor and update project progress with automated status tracking.

pwnk77/agentic-workflows · 13 tokens

task-manager

Task Manager skill - Create, track, and manage development tasks linked to PRDs.

pwnk77/agentic-workflows · 16 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

todo-for-ai-agent-runtime