milestone-runner

milestone-runner is a command for coding agents from minhoyoo-iotrust/claude-plugin. It costs 36 tokens per session (2,704 once invoked), scanned A, original, MIT.

A command that processes planned objectives one at a time through a development workflow. A milestone is a defined piece of work; GSD is the required project workflow system, and GitHub CLI handles pull requests and merges.

In plain words
What is it for?
Use it to find objectives marked PLANNED, create and complete milestones, open pull requests, run CI, merge changes, and update the base branch. It requires GSD and an authenticated GitHub CLI.
Why use it?
It removes the need to repeat the same milestone steps manually and helps keep sequential objectives moving through review and integration.

Command

Part of the gsdu plugin — 1 skill, 2 commands shipped together

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/minhoyoo-iotrust/claude-plugin/milestone-runner
Clone the repo
git clone --depth 1 https://github.com/minhoyoo-iotrust/claude-plugin

Or install gsdu, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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-runner

README.md
[![agentmods](https://agentmods.dev/badge/commands/minhoyoo-iotrust/claude-plugin/milestone-runner.svg)](https://agentmods.dev/commands/minhoyoo-iotrust/claude-plugin/milestone-runner)
Your own site
<a href="https://agentmods.dev/commands/minhoyoo-iotrust/claude-plugin/milestone-runner"><img src="https://agentmods.dev/badge/commands/minhoyoo-iotrust/claude-plugin/milestone-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,704 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 $0.00036 $0.02704
Opus 5 $0.00018 $0.01352
Sonnet 5 $0.00007 $0.00541
Haiku 4.5 $0.00004 $0.00270

Measured 5d ago against content hash 10b396827898, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

milestone-runner 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 5d 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.

plugins/gsdu/commands/milestone-runner.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL INSTRUCTION: Do NOT use the Skill tool to invoke gsdu:milestone-runner. Do NOT re-invoke this command. All workflow steps are below — execute them directly.

For each PLANNED objective: new-milestone → autopilot → complete-milestone → PR → CI → merge → pull base branch.

Orchestrator stays lean. Each milestone phase is delegated via existing GSD skills.

Prerequisites:

  • GSD must be installed (~/.claude/get-shit-done/ exists)
  • Objective documents with status: PLANNED in frontmatter
  • gh CLI authenticated for PR/merge operations

If --base <branch> argument is provided, use that value. Otherwise, auto-detect the repo's default branch:

BASE_BRANCH=$(gh repo view --json defaultBranch -q '.defaultBranch')
echo "BASE_BRANCH=${BASE_BRANCH}"

Store BASE_BRANCH for use throughout the workflow. All subsequent references to the target branch use ${BASE_BRANCH}.

# Check GSD installation
test -f "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" || echo "GSD_NOT_FOUND"

# Check gh CLI
gh auth status 2>&1 | head -3

If GSD_NOT_FOUND:

GSD is not installed. Install it first:
  https://github.com/gsd-build/get-shit-done

Exit.

2. Determine objectives directory:

Use --objectives <dir> argument if provided, otherwise objectives/.

ls ${OBJECTIVES_DIR}/*.md 2>/dev/null

If no files found, exit with error.

3. Scan for PLANNED objectives:

Read each .md file in the objectives directory. Parse YAML frontmatter for status: PLANNED.

Build execution queue:

  • Filter: only status: PLANNED documents
  • Sort: by filename ascending (natural order)
  • If --from <prefix> given: skip files before the matching prefix

For each objective, extract:

  • filename — e.g., m01-26-brave-search-integration.md
  • title — first # heading in the document
  • version — extract from frontmatter version field if present; otherwise derive from filename pattern:
    • Pattern m{major}-{minor}-*v{major}.{minor} (e.g., m01-26-*v1.26)
    • Pattern v{version}-* → use as-is
    • If no pattern matches: report error and ask user
  • slug — derive from filename (strip prefix and extension, kebab-case)
  • content — full file content (for milestone context)

If queue is empty:

No PLANNED objectives found in ${OBJECTIVES_DIR}/.
All objectives may already be SHIPPED or IN_PROGRESS.

Exit.

## Milestone Runner — Execution Plan

| # | Filename | Version | Title |
|---|----------|---------|-------|
| 1 | m01-26-brave-search-integration.md | v1.26 | 시장 데이터 파운데이션 |
| 2 | m01-27-market-analysis-engine.md | v1.27 | 시장 분석 엔진 |
| ... | ... | ... | ... |

**Steps per milestone:**
1. Write MILESTONE-CONTEXT.md from objective content
2. /gsd:new-milestone (version + context)
3. /gsdu:autopilot
4. /gsd:complete-milestone
5. Create PR → Wait CI → Merge (--merge) → Checkout ${BASE_BRANCH} → Pull

Read the full file on GitHub · 358 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. 5d ago First seen · 358 lines · 36 tokens per session scan A 10b396827898

Subscribe to this mod's changes

milestone-runner is a command published in the GitHub repository minhoyoo-iotrust/claude-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 2,704 once invoked, about $0.0002 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.