add

Drives spec-first, test-driven development tasks through a state-tracked .add/ bundle with frozen contracts and evidence-based gates.

19|5|Updated May 29, 2026
One-click install
npx skills add https://github.com/pilotspace/ADD --skill add-pilotspace
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add
Source: https://github.com/pilotspace/ADD/tree/main/add-method/skill/add
Command: npx skills add https://github.com/pilotspace/ADD --skill add-pilotspace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? AI-assisted coding degrades across long sessions: requirements drift, earlier promises get silently broken, and trust rests on plausible-looking diffs. ADD keeps all project state on disk in a .add/ bundle so every change is driven by a frozen specification, red tests, and a recorded pass/fail receipt rather than conversation memory. ## Core Features & Use Cases - 3-beat task loop: Direction (rules, contract, red tests, one human freeze approval) → Build (code to green inside frozen scope) → Verify (evidence receipt, residue checks, recorded gate verdict of PASS, RISK-ACCEPTED, or HARD-STOP). - Intake lanes and session resume: routes requests to Quick, Task, Explore, or Milestone lanes based on size and sensitivity, and resumes any session from the bundle alone via add status. - Living specs and personas: lessons are filed as tagged deltas (DDD/SDD/UDD/TDD/ADD) that humans fold into specs, and project-fit persona lenses advise beats without ever lowering a gate. - Use Case: A team building a multi-milestone feature asks the agent to "start a task" for each slice; ADD freezes an approved contract per task, runs the test suite red then green, and records a JUnit-based receipt so milestone six never silently breaks milestone one. ## Quick Start Ask the agent to run add status to orient from the .add bundle, then describe the change you want so it can size the request and create a task.

Frequently Asked Questions about add

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

FAQPage Schema
How do I start a spec-first TDD task with the ADD method?▼

Run add status to orient, then let intake size the request into a lane. For a Task, create it with add new Task <slug>, author RULES, PLAN and red CHECKS, get the single human freeze approval, then build to green and record a gate verdict.

How does ADD resume work across AI coding sessions?▼

ADD stores all state on disk in the .add/ bundle, so a new session resumes by running add status, which reads the bundle rather than the repository or chat history. The next required beat is derived from the node's recorded stamps.

Does ADD work for non-code domains like finance or documentation?▼

Yes, the doc profile ships for non-code work and the trust spine is domain-neutral. You write a small checker script that emits JUnit XML against thresholds frozen in the task's rules, and add run parses it like any test runner.

What happens when a security issue is found during verification?▼

A security finding is always a HARD-STOP that only a human can resolve. It cannot be signed away as RISK-ACCEPTED, softened by a persona, or bypassed by a delegate subagent at any beat.

When should I not use the ADD workflow?▼

Tiny mechanical changes of three or fewer adjacent files with zero unknowns can use the Quick lane, which skips node creation and records only a commit plus one learn line. Full ceremony is reserved for contract-bearing or sensitive work.