commitment-tracker

Scan outgoing replies for commitments and execute or rewrite them.

5|1|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/netanel-abergel/pa-skills --skill commitment-tracker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: commitment-tracker
Source: https://github.com/netanel-abergel/pa-skills/tree/main/skills/commitment-tracker
Command: npx skills add https://github.com/netanel-abergel/pa-skills --skill commitment-tracker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents conversational agents from promising actions they do not perform by detecting commitment language in outgoing replies and forcing immediate execution, providing accountability and reducing missed follow-ups.

Core Features & Use Cases

  • Immediate Execution: Scan replies for trigger phrases and execute the promised action before sending the message.
  • Intent Logging & Recovery: Record pending commitments to a durable commitments.jsonl ledger and recover incomplete actions on startup or heartbeat.
  • Safe Failure Handling: If execution is impossible, rewrite the reply to avoid promises and notify the owner with the blocking reason.
  • Use Case: When an agent intends to "I'll send the report", it will attach or send the report immediately, log the action, and then respond "Sent ✅" instead of making an unverifiable promise.

Quick Start

Before sending any reply that includes a promise, execute the promised action immediately, append a pending intent to the commitments.jsonl file, and then report the result in your response.

Frequently Asked Questions about commitment-tracker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent conversational agents from making unfulfilled promises in outgoing replies?

To prevent unfulfilled promises, you can enforce execution of commitments by scanning outgoing replies for trigger phrases and executing the promised action synchronously before the message is sent.

How does intent logging and recovery work for missed agent follow-ups?

Intent logging records pending commitments to a durable commitments.jsonl ledger, allowing the system to recover and execute incomplete actions during startup or heartbeat checks.

What happens when an agent cannot execute a promised action in a direct message?

When execution is impossible, safe failure handling rewrites the outgoing reply to remove the promise and notifies the owner with the specific blocking reason.

Can I automate cross-agent communication accountability for delivery commitments?

Yes, you can automate cross-agent accountability by detecting commitment language in outgoing messages, performing the action immediately, and logging the intent for recovery.

What is the best way to track agent reliability for internal actions and follow-ups?

The best way to track agent reliability is logging intent and completion to a commitments.jsonl file, ensuring accountability and reducing missed follow-ups across internal actions.

Do I need dependencies or specific components to enforce immediate commitment execution?

No dependencies or components are required to enforce immediate commitment execution; the skill operates independently by scanning replies and logging to a local jsonl file.