ms-add

ms-add is a command for coding agents from thixpin/pitway. It costs 0 tokens per session (356 once invoked), scanned A, a copy of milestone-add, MIT.

A command for registering the next draft milestone from a contract and a task plan. A milestone is a planned stage of work; the command records it without confirming it or allowing work to start.

In plain words
What is it for?
Use it to add or replace a draft milestone, attach its planning files, or prepare it for later confirmation or cancellation.
Why use it?
It keeps planning separate from approval, so an unreviewed milestone cannot be treated as ready. It also lets you correct a draft without creating a new ID.

Command

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 commands/thixpin/pitway/ms-add
Clone the repo
git clone --depth 1 https://github.com/thixpin/pitway
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00356
Opus 5 $0.00000 $0.00178
Sonnet 5 $0.00000 $0.00071
Haiku 4.5 $0.00000 $0.00036

Measured 3d ago against content hash 46129570ab6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ms-add 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.

Origin

This is a copy

100% identical to milestone-add — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/integrations/claude/commands/ms-add.md · 37 lines

What it actually says


description: PitWay: Create the next milestone from a drafted contract and task plan

milestone-add

Role: Main Agent

pitway milestone-add --contract <path> --tasks <path> [--requirement <path>] [--replace <id>] [--json]

Call this once a requirement has been broken down into a drafted contract and a right-sized task graph, and you're ready to register the next milestone. It creates the milestone in draft status — nothing is confirmed yet, and no task work may start.

This is a planning-stage command, not a decision gate itself: the gate comes next, at milestone-confirm, which requires the developer to have actually seen and approved the contract you just registered. See ../protocol-driver.md for the full lifecycle and the decision-gate rule.

--replace <id> corrects an existing draft in place under the same id (mistakes in a not-yet-confirmed draft) — it never mints a new id and never touches git. It only works while <id> is still draft; once confirmed, use milestone-confirm --amend instead. To abandon a draft permanently instead of correcting it, use milestone-cancel.

Scope entries (write_scope, context_files, relevant_files) must name files, never directories -- Core matches dirty paths exactly, so a directory entry can never be satisfied at execution; the command refuses it by name (M045). Files that do not exist yet are fine.

Draft contract/tasks file formats: ../draft-formats.md. Run pitway milestone-add --help for flags.

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 · 37 lines · 0 tokens per session scan A 46129570ab6a

Subscribe to this mod's changes

ms-add is a command published in the GitHub repository thixpin/pitway (19 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 356 tokens. A static security scan graded it A with 0 findings. It is 100% identical to milestone-add, differing in 0 lines, and is treated as a copy.