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.
npx skills add xiaohuxi/release-evidence-pack-mcp --skill release-readiness-reviewgit clone --depth 1 https://github.com/xiaohuxi/release-evidence-pack-mcpWrote 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.
[](https://agentmods.dev/skills/xiaohuxi/release-evidence-pack-mcp/release-readiness-review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Confirm the repository root, Git base revision, intended release scope, and available JUnit XML reports.
- Call
inspect_release_changesto identify changed code, database migrations, contracts, configuration, deployment files, and tests. - Call
summarize_test_reportsfor every supplied report. Do not treat console text or an unverified statement such as “tests passed” as machine-readable evidence. - Call
build_release_evidence_packwith the same base revision and report list. - 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.
- Add evidence the MCP cannot infer: CI URL, artifact identifier and digest, change ticket, owners, deployment window, monitoring signals, and rollback authority.
- Produce the report using references/review-template.md.
- End with exactly one decision:
GO,CONDITIONAL GO, orNO-GO.
Decision Rules
- Return
NO-GOwhen any blocker remains unresolved. - Return
CONDITIONAL GOonly when every condition has an owner, deadline, and objective verification step. - Return
GOonly 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, notverified. - 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.
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.
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.
- 11d ago First seen · 106 lines · 64 tokens per session scan A b013d8192e5a
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.