milestone-pipeline

milestone-pipeline is a command for coding agents from chris-dare-dev/agent-kit. It costs 52 tokens per session (10,527 once invoked), scanned A, original, MIT.

A command that runs a fixed delivery process for a software milestone: research, implementation, independent review, corrections, publishing, applying, and verification. It keeps code completion separate from a change being published, deployed, and confirmed in operation.

In plain words
What is it for?
Use it for substantial, named milestones when you need to distinguish planning, code completion, publication, deployment, operational verification, and final completion.
Why use it?
It prevents a local commit or passing checks from being treated as proof that a live system has been updated successfully. It also assigns state tracking and approval boundaries to the main agent.

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/chris-dare-dev/agent-kit/milestone-pipeline
Clone the repo
git clone --depth 1 https://github.com/chris-dare-dev/agent-kit

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-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/chris-dare-dev/agent-kit/milestone-pipeline.svg)](https://agentmods.dev/commands/chris-dare-dev/agent-kit/milestone-pipeline)
Your own site
<a href="https://agentmods.dev/commands/chris-dare-dev/agent-kit/milestone-pipeline"><img src="https://agentmods.dev/badge/commands/chris-dare-dev/agent-kit/milestone-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,527 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 $0.00052 $0.10527
Opus 5 $0.00026 $0.05264
Sonnet 5 $0.00010 $0.02105
Haiku 4.5 $0.00005 $0.01053

Measured 3d ago against content hash c33da08205d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

milestone-pipeline 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.

data/commands/milestone-pipeline.md · 827 lines

How it starts

The opening of the file, as written. The whole thing — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone pipeline orchestrator — delivery-state v2

The main session is the sole orchestrator, state writer, findings reconciler, and owner of every human authorization boundary. Subagents never spawn other subagents, advance state, push, apply, or self-certify closure.

This pipeline separates the delivery claims:

code-complete -> published -> applied -> operationally-verified -> complete

A local commit, green check, push, rendered GitOps revision, applied workload, and verified behavior are different facts. plan-reviewed is a mandatory control gate, not a synonym for any delivery claim. Never collapse these facts into one checkbox or a free-text external-write ledger.

Read before running:

  • data/references/pipeline-pattern-v2.md
  • data/references/runtime-contract.md
  • data/references/milestone-pipeline-state-schema.md
  • data/references/milestone-pipeline-artifacts-v2.md
  • data/references/milestone-pipeline-agent-contract.md
  • data/references/milestone-pipeline-critique-format.md

Arguments and scope

  • ID: required stable milestone id; everything before the first --.
  • --deep: one deep researcher instead of the standard two-agent fan-out.
  • --resume: inspect state and resume at its current phase; never replay a completed phase.

If no id was supplied, stop and ask for it. Invoke for non-trivial work with a fixed outcome: a new module/endpoint/chart, a cross-cutting refactor, or a delivery milestone. Do not invoke for typos, lint-only edits, simple dependency bumps, reverts, or direct work in deploy/argocd-config-* (the initializer refuses generated deploy repos by identity).

Required CWD for Claude is inside the target git repo. The Codex adapter runs from the workspace root and passes an absolute --repo-root; it uses git -C for target-repo commands. In both cases:

WS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"
REPO_ROOT="${REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"
[ -d "$WS" ] || { echo "Set PERSONAL_WORKSPACE_ROOT" >&2; exit 1; }
[ -d "$REPO_ROOT" ] || { echo "Set REPO_ROOT to the target git repo" >&2; exit 1; }
STATE="$REPO_ROOT/.claude/notes/milestones/$ID/state.json"

Read the full file on GitHub · 827 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 · 827 lines · 52 tokens per session scan A c33da08205d9

Subscribe to this mod's changes

milestone-pipeline is a command published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 25d ago), licensed MIT. It adds 52 tokens to every session and 10,527 once invoked, about $0.0003 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 2026-08-31.