release-review

release-review is a skill for Claude Code from ddddjaak/se-skills. It costs 128 tokens per session (3,707 once invoked), scanned A, original, MIT.

A checklist-based review of a release package, including its binary, release notes, version manifest, and test reports. It checks that the files agree with one another and can be traced back to requirements.

In plain words
What is it for?
Use it as a final gate before external distribution or milestone sign-off, such as an alpha or beta release.
Why use it?
It exposes release gaps such as stale version information, skipped tests without explanation, or undocumented regressions before customers receive the package.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the se-skills plugin — 16 skills, 6 commands, 5 agents, 1 hook, 3 MCP servers shipped together

Good fit Use it as a final gate before external distribution or milestone sign-off, such as an alpha or beta release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ddddjaak/se-skills/release-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 ddddjaak/se-skills --skill release-review
Clone the repo
git clone --depth 1 https://github.com/ddddjaak/se-skills

Made for: Claude Code.

Or install se-skills, the plugin that ships this one along with the rest of its 16 skills, 6 commands, 5 agents, 1 hook, 3 MCP servers.

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 release-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ddddjaak/se-skills/release-review/github.svg)](https://agentmods.dev/skills/ddddjaak/se-skills/release-review)
Your own site
<a href="https://agentmods.dev/skills/ddddjaak/se-skills/release-review"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/release-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 release-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ddddjaak/se-skills/release-review"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/release-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,707 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 $0.00128 $0.03707
Opus 5 $0.00064 $0.01853
Sonnet 5 $0.00026 $0.00741
Haiku 4.5 $0.00013 $0.00371

Measured 10d ago against content hash cc5524f443bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

release-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 10d 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.

skills/release-review/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Review

Overview

A release package that "looks complete" often is not. The binary boots but the version manifest is stale. The test report says "all passed" but 3 test cases were skipped without justification. The release notes mention new features but omit known regressions. These gaps are invisible to a quick sanity check and devastating when the release reaches a customer.

This skill performs a systematic, checklist-driven release readiness review: inventory every artifact, verify internal consistency (do versions match? do test results trace to requirements?), and cross-reference against two structured checklists. The output is a release review report that gives the release owner a concrete list of what must be fixed before the release can ship — and what can be accepted as a known trade-off.

This skill is the release-phase counterpart to design-review: it is adversarial review applied to the release package, not the design artifact.

When to Use

  • A release package has been assembled (binary, release notes, version manifest, test reports) and the team needs a gate review before external distribution
  • Preparing for a milestone release sign-off (Alpha, Beta, RC, GA)
  • A release candidate has been cut and must be verified for completeness, consistency, and traceability
  • A previous release had a field issue and the team wants a structured review before the next release
  • A downstream consumer (FAE, customer, manufacturing) reports that the release package is incomplete or inconsistent

When NOT to use:

  • The release package has not been assembled yet (checklist items will all read "N/A" — wait until the package exists)
  • Reviewing a single hotfix patch without a full release package (use design-review for the patch diff)
  • Source-level code review (use a code review process, not release readiness review)
  • Requirements or architecture review (use requirements-decompose, architecture-design, or design-review)
  • Pure information lookup ("what version is the SPI driver binary?" — check the manifest directly)

Read the full file on GitHub · 263 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. 10d ago First seen · 263 lines · 128 tokens per session scan A cc5524f443bb

Subscribe to this mod's changes

release-review is a skill published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 3,707 once invoked, about $0.0006 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.