milestone

milestone is a skill for Claude Code, Codex from MountainUnicorn/add. It costs 20 tokens per session (2,803 once invoked), scanned A, original, MIT.

A project-management skill for managing milestones, which are planned groups of work with goals, features, and completion criteria.

In plain words
What is it for?
Listing milestone status, changing the active milestone, splitting large milestones, changing feature scope, and creating new milestones.
Why use it?
It helps keep project scope and progress aligned with the roadmap when work needs to be split, moved, or resized.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mountainunicorn/add/milestone
Any agent
npx skills add MountainUnicorn/add --skill milestone
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

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.

agentmods badge for milestone

README.md
[![agentmods](https://agentmods.dev/badge/skills/mountainunicorn/add/milestone.svg)](https://agentmods.dev/skills/mountainunicorn/add/milestone)
Your own site
<a href="https://agentmods.dev/skills/mountainunicorn/add/milestone"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/milestone.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.02803
Opus 5 $0.00010 $0.01401
Sonnet 5 $0.00004 $0.00561
Haiku 4.5 $0.00002 $0.00280

Measured 3d ago against content hash c4c6a1118809, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

milestone 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 3d 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.

core/skills/milestone/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Milestone Command v{{VERSION}}

Manage milestones directly — list status, switch active milestone, split large milestones, rescope features, or create new ones. This is the tactical companion to /add:roadmap (strategic horizon planning).


Pre-Flight

All subcommands start here:

  1. Read .add/config.json — extract maturity.level, planning.current_milestone, planning.current_cycle
    • If not found: abort with "No ADD project found. Run /add:init first."
  2. Glob docs/milestones/M*.md — discover all milestone files
  3. Parse each milestone file — extract:
    • Status (NOT_STARTED / IN_PROGRESS / COMPLETE)
    • Goal (first line under ## Goal)
    • Features (from Feature Detail table: name, position, spec link)
    • Success criteria (count checked [x] vs total [ ])
  4. Read docs/prd.md Section 6 — cross-reference horizon placement (Now/Next/Later) from the roadmap table
  5. Read .add/handoff.md if it exists — note any in-progress decisions relevant to milestone changes
  6. Determine subcommand from arguments. Default: --list

Command: /milestone --list (default)

Display all milestones with live status. No file modifications.

Output

Milestones Overview
Active: {planning.current_milestone or "None"}

| # | Milestone | Status | Horizon | Features | Complete | Target |
|---|-----------|--------|---------|----------|----------|--------|
| → | M1-foundation | IN_PROGRESS | NOW | 5 | 40% (2/5) | alpha |
|   | M2-scaling | NOT_STARTED | NEXT | 3 | 0% (0/3) | beta |
|   | M3-enterprise | NOT_STARTED | LATER | 4 | 0% (0/4) | ga |
  • marks the active milestone
  • Completion % = features at VERIFIED or DONE / total features
  • Horizon comes from PRD roadmap table; show "?" if milestone not in PRD

Maturity Scaling

  • POC/Alpha: Table as shown above
  • Beta/GA: Add columns for Appetite Remaining, Risk Count, Cycle Count

Command: /milestone --switch

Switch the active milestone. Accepts milestone ID like M2-scaling or just M2.

Read the full file on GitHub · 318 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. 3d ago First seen · 318 lines · 20 tokens per session scan A c4c6a1118809

Subscribe to this mod's changes

milestone is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,803 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.