milestone-review

milestone-review is a skill for Claude Code from cenconq25/claude-code-app-studio. It costs 45 tokens per session (1,909 once invoked), scanned A, original, MIT.

A read-only review of progress toward a project milestone, such as an alpha, beta, release candidate, or final release. It checks completeness, quality, readiness, and risks, then gives a go/no-go recommendation.

In plain words
What is it for?
Use it near a milestone deadline or when deciding whether the project is ready for its next stage.
Why use it?
It brings evidence from plans, requirements, bugs, and testing into one checkpoint review before the team advances.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it near a milestone deadline or when deciding whether the project is ready for its next stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cenconq25/claude-code-app-studio/milestone-review
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.

Any agent
npx skills add cenconq25/claude-code-app-studio --skill milestone-review
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/milestone-review/github.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/milestone-review)
Your own site
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/milestone-review"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/milestone-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for milestone-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/milestone-review"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/milestone-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.01909
Opus 5 $0.00023 $0.00955
Sonnet 5 $0.00009 $0.00382
Haiku 4.5 $0.00005 $0.00191

Measured 6d ago against content hash 1ec3bbebe58d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

milestone-review 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 6d 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.

.claude/skills/milestone-review/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone Review

A milestone is bigger than a sprint and smaller than a release — it represents a meaningful checkpoint (alpha, internal beta, public beta, RC, GM). This skill assesses readiness across feature completeness, quality, store-readiness, and risk, then produces a go/no-go.

Read-only.


Purpose / When to Run

Run when:

  • A milestone deadline is approaching
  • The team needs to decide alpha → beta → RC progression
  • Stakeholders need a status pack
  • A retrospective on a missed milestone is being prepared

Distinct from /sprint-status (one sprint) and /launch-checklist (final pre-release in the second skill set). This skill assesses a milestone, not a single sprint or a release.

Inputs

  • production/milestones/<milestone>.md if present
  • All sprint plans up to now
  • All epics
  • All stories
  • All PRDs and ADRs (for completeness checks)
  • production/qa/ (test evidence, bugs)
  • production/releases/ (any prior milestone artifacts)

Outputs

  • A printed structured review

Phase 1: Resolve Milestone

If named, read production/milestones/<name>.md. If unnamed:

  • Glob production/milestones/*.md. Pick the most recent (or the one with status Active).
  • If none exist, ask the user to describe the milestone or run with the default "current state" framing.

A milestone doc typically contains: target date, success criteria, scope (epics in scope), exit criteria.

If there is no milestone doc, ask the user which milestone is being reviewed and capture an inline definition (target date + success criteria).


Phase 2: Feature Completeness

For each epic in milestone scope:

  • Total stories
  • Stories Complete
  • Stories In Progress
  • Stories Blocked
  • Stories Ready (not started)
  • Untraced PRD requirements (from epic Section 6)

Compute % complete per epic. Flag any epic <80% complete with <2 weeks remaining.

For each PRD in scope:

  • Are all v1 TR-IDs covered by stories?
  • Are all stories Complete? If not, gap list.

Phase 3: Quality Metrics

Read the full file on GitHub · 261 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. 6d ago First seen · 261 lines · 45 tokens per session scan A 1ec3bbebe58d

Subscribe to this mod's changes

milestone-review is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,909 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 2026-09-03.

Related

Other skills, from other repositories