rigor: Skill for Claude Code

.claude/skills/rigor-release-prep/SKILL.md

rigor-release-prep is a skill for Claude Code from rigortype/rigor. It costs 61 tokens per session (9,570 once invoked), scanned A, original, MPL-2.0.

A release checklist for publishing a RubyGems package, including version updates, changelog cleanup, and release checks. It requires the user to approve pending decisions before the release proceeds.

In plain words
What is it for?
Use it to prepare a Rigor gem release, review the approval queue, combine changelog fragments, and run the project's release gates.
Why use it?
It prevents an agent from releasing with unapproved changes or skipping required checks. It is only meant for an explicitly requested release, not routine development work.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions AGENTS.md.

This is rigortype/rigor's own configuration. It tells Claude Code how to work on rigor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rigor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rigortype/rigor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rigortype/rigor/master/.claude/skills/rigor-release-prep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rigortype/rigor

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 rigor-release-prep

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-release-prep"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-release-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,570 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 $0.00061 $0.09570
Opus 5.5 $0.00024 $0.03828
Sonnet 5.5 $0.00012 $0.01914
Haiku 4.5 $0.00006 $0.00957

Measured today against content hash fcf5c5ada5a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rigor-release-prep 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 today.

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/rigor-release-prep/SKILL.md · 694 lines

How it starts

The opening of the file, as written. The whole thing — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rigor Release Prep

Follow this workflow when preparing a new rigor gem release.

All commands MUST run through the Flake per AGENTS.md. The examples below include the full nix develop --command prefix so each line is directly runnable from outside the Flake shell. Inside the Flake shell, drop the prefix.

First: ratify the approval queue

Before any other step, report the approval queue and let the user decide each entry. Agents make every decision that list does not call serious on their own and record it in approval-queue.d/ (docs/agents/contribution-flow.md § "Decisions and the approval queue", ADR-123); a release ships only decisions the user ratified.

git fetch origin
git ls-tree --name-only origin/master approval-queue.d/   # README.md alone means empty
  1. Empty (only README.md): say so in one line and go on to the branch. Entries the user ratified earlier in a long window are already gone: a Ratify approval queue entries PR deleted them on master (approval-queue.d/README.md), so only what remains is reported here.
  2. Otherwise, report every entry in the user's language — the language they write to you in, not the repository's English. Read each file from origin/master and, per entry, give its decision, PR, class and precedent, then its background, the options with their trade-offs, the decision's reasoning and how to undo it. Translate faithfully and keep every link; do not shorten the trade-offs away, they are what the user is judging.
  3. Ask for each entry with options Ratify, Revise and Revert, in the user's language: under Claude Code with AskUserQuestion (up to four entries per call, free text always allowed), elsewhere as a numbered question in chat. Do not recommend an option.
  4. Ratified entries are deleted on the release branch once it is cut (below), in one commit Ratify approval queue entries whose body lists each entry's title and PR link: that commit is the record of the ratification.
  5. Revise or Revert: the change lands as an ordinary PR (contribution-flow § "Landing a pull request") that changes or reverts the decision and deletes its entry. File an issue for it when the user does not want it done now. Either way the release waits: tell the user so, and continue the other steps only if they want the release prepared while the PR lands.
  6. The release ships with the queue empty. Before opening the release PR, and again before publishing, list approval-queue.d/ on the release branch and on origin/master: an entry that landed on master after step 3 goes through steps 2–5 too; rebase the release branch onto origin/master to pick it up before deleting it there. spec/docs/approval_queue_spec.rb fails the release PR's CI while its branch holds an entry, but it cannot see an entry that reaches master afterwards.

Read the full file on GitHub · 694 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. today Changed · +5 lines fcf5c5ada5a0
  2. 11d ago First seen · 689 lines · 61 tokens per session scan A b3bd4eb7519c

Subscribe to this mod's changes

rigor-release-prep is a skill published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 61 tokens to every session and 9,570 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.

Related

rigor-release-prep compared with skills from other repositories

rigor-release-prep next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rigor-release-preprigortype/rigorSkill107todayMPL-2.0A61Claude Code
release-announcementpaperclipai/paperclipSkill111ktodayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114ktodayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25ktodayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill788yesterdayMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7ktodayApache-2.0A22Claude Code, Codex