release-readiness-review

release-readiness-review is a skill for Codex from xiaohuxi/release-evidence-pack-mcp. It costs 64 tokens per session (1,208 once invoked), scanned A, original, MIT.

A review skill that uses Git changes and machine-readable test reports to decide whether a software release is ready to proceed.

In plain words
What is it for?
Reviewing code, database migrations, APIs, configuration, deployment files, and tests; summarizing JUnit reports; assembling release evidence; and producing a go or no-go decision.
Why use it?
It replaces informal claims that tests passed with checked evidence and highlights release blockers, approval needs, and rollback concerns.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Reviewing code, database migrations, APIs, configuration, deployment files, and tests; summarizing JUnit reports; assembling release evidence; and producing a go or no-go decision.

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

Made for: Codex.

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-readiness-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaohuxi/release-evidence-pack-mcp/release-readiness-review"><img src="https://agentmods.dev/badge/skills/xiaohuxi/release-evidence-pack-mcp/release-readiness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,208 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 $0.00064 $0.01208
Opus 5 $0.00032 $0.00604
Sonnet 5 $0.00013 $0.00242
Haiku 4.5 $0.00006 $0.00121

Measured 11d ago against content hash b013d8192e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

release-readiness-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 11d 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-readiness-review/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Readiness Review

Use release-evidence-pack-mcp as the evidence source. Keep the review read-only and separate verified evidence from human assumptions.

Workflow

  1. Confirm the repository root, Git base revision, intended release scope, and available JUnit XML reports.
  2. Call inspect_release_changes to identify changed code, database migrations, contracts, configuration, deployment files, and tests.
  3. Call summarize_test_reports for every supplied report. Do not treat console text or an unverified statement such as “tests passed” as machine-readable evidence.
  4. Call build_release_evidence_pack with the same base revision and report list.
  5. Review every MCP finding and classify unresolved items:
    • Blocker: failed tests, destructive DDL without an approved rollback/forward-fix, exposed secret material, or an artifact that cannot be reproduced.
    • Approval required: source, API, configuration, deployment, or schema changes with incomplete evidence.
    • Advisory: low-risk documentation or metadata changes with adequate validation.
  6. Add evidence the MCP cannot infer: CI URL, artifact identifier and digest, change ticket, owners, deployment window, monitoring signals, and rollback authority.
  7. Produce the report using references/review-template.md.
  8. End with exactly one decision: GO, CONDITIONAL GO, or NO-GO.

Decision Rules

  • Return NO-GO when any blocker remains unresolved.
  • Return CONDITIONAL GO only when every condition has an owner, deadline, and objective verification step.
  • Return GO only when required tests pass, the deployable artifact is identifiable, migration risk is covered, and rollback steps are actionable.
  • Never lower a risk level merely because a deployment is urgent.
  • Never invent CI results, artifact digests, approvals, or rollback commands.

Evidence Boundaries

  • Cite file paths, report names, revisions, and finding codes from the MCP output.
  • Mark information supplied only by a person as declared, not verified.
  • Mark unavailable information as missing; do not infer success from absence.
  • Keep testcase logs, secrets, tokens, credentials, and private configuration values out of the report.
  • Do not modify the repository, run deployment commands, approve a change ticket, or trigger CI unless the user separately requests it.

Read the full file on GitHub · 106 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 106 lines · 64 tokens per session scan A b013d8192e5a

Subscribe to this mod's changes

release-readiness-review is a skill published in the GitHub repository xiaohuxi/release-evidence-pack-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,208 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.