model-a-protocol SKILL.md skillA

model-a-protocol from joelhooks/rat-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add joelhooks/rat-stack/model-a-protocol@git:20261108.c11e293

Pins git:20261108.c11e293 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
joelhooks/rat-stack
Path
skills/model-a-protocol/SKILL.md
Versions recorded
2
Latest version
git:20261108.c11e293, committed Nov 8, 2026
First version recorded
Nov 8, 2026
Size
7,293 bytes
Repository stars
216
License
MIT

Check a protocol with a small TLA+ model before you build or change it. Use when steps can interleave or die halfway, such as a crash between two writes, a retry after an unknown outcome, an alarm or sweep that redrives work, or two writers on one record. Also use when asked "can this race?", "what if it dies here?", or "model this", or before a durability design review.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Model a protocol

A protocol is a set of steps that share state, such as a request, a background delivery, a sweep and an erase on one record. Example tests run one order of those steps. A model checker runs every order within small bounds, including a crash between any two steps. It finds interleaving bugs that reading and example tests miss.

The worked example is the join-intake model in `packages/core/spec/`. Its `README.md` shows each part of this skill on real code. Its test is `packages/core/test/join-intake-spec.test.ts`.

## When to model

Model a protocol when its steps can interleave or stop halfway:

- A crash can land between two writes.
- A retry re-sends after an unknown outcome.
- An alarm, a cron sweep, or `waitUntil` finishes work the request started.
- Two writers can change one record.

Model it before the design review, so reviewers argue over a trace instead of prose. A pure fold, a read path, or a single atomic write does not need a model. Use a [property](/lore/property-based-testing) or a [model test](/lore/model-based-testing) for those.

A fix to a protocol that has no model does not wait for one. Land the fix with its failing-then-passing test.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_7paig7axct3rfao4/678baf867f08bd5af59e2adfbc638f2d55dab46093e596e6687dbd76e2f49c91.json

Then /plugin install model-a-protocol@markdownregistry-7paig7axct3rfao4 in Claude Code. It installs git:20261108.c11e293, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add joelhooks/rat-stack/model-a-protocol@sha256:678baf867f08bd5a

The line at the top of this page pins the label git:20261108.c11e293, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7paig7axct3rfao4.svg)](https://markdownregistry.com/a/art_7paig7axct3rfao4)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in joelhooks/rat-stack/model-a-protocol since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of model-a-protocol from somewhere else? Ask it: where did my model-a-protocol come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, all committed on Nov 8, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261108.c11e293 latest2026-11-08 c11e293 7,293 BA view · diff
git:20261108.49268da2026-11-08 49268da 7,047 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7293 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

joelhooks/rat-stack · 216 stars · license MIT · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7paig7axct3rfao4
GET https://markdownregistry.com/api/v1/resolve?ref=joelhooks/rat-stack/model-a-protocol
GET https://markdownregistry.com/api/v1/blob/678baf867f08bd5af59e2adfbc638f2d55dab46093e596e6687dbd76e2f49c91

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from joelhooks/rat-stack

AGENTS.md AGENTS.md file
joelhooks/rat-stack · AGENTS.md
git:20261118.2c2a871 · audit B · 216 stars
CLAUDE.md CLAUDE.md file
joelhooks/rat-stack · CLAUDE.md
git:20260830.14a08e5 · audit B · 216 stars
AGENTS.md@apps/web/src AGENTS.md file
joelhooks/rat-stack · apps/web/src/AGENTS.md
git:20261103.67d126f · audit A · 216 stars
AGENTS.md@examples/tokenmaxx-starter AGENTS.md file
joelhooks/rat-stack · examples/tokenmaxx-starter/AGENTS.md
git:20261116.b6dac3f · audit A · 216 stars
add-a-capability SKILL.md skill
joelhooks/rat-stack · skills/add-a-capability/SKILL.md · Learn how one contract and its handler become a command, HTTP route, MCP tool, browser RPC, and sandbox call.
git:20261103.d13054d · audit A · 216 stars
add-a-feature-flag SKILL.md skill
joelhooks/rat-stack · skills/add-a-feature-flag/SKILL.md · Declare a typed feature flag, its scoped evidence ladder, approval roles, removal date, and durable ledger adapter.
git:20261025.777b9ba · audit A · 216 stars
add-a-lifecycle-machine SKILL.md skill
joelhooks/rat-stack · skills/add-a-lifecycle-machine/SKILL.md · Learn how XState owns a lifecycle while Effect owns its work, errors, and services.
git:20261108.49268da · audit A · 216 stars
add-a-store SKILL.md skill
joelhooks/rat-stack · skills/add-a-store/SKILL.md · Add persistence through a service named for an application job, with validation, vendor Layers, migrations, bounded…
git:20261008.f1a00f2 · audit A · 216 stars
durability SKILL.md skill
joelhooks/rat-stack · skills/durability/SKILL.md · Keep a rat-stack app standing when a provider, pool, or dependency slows down or a worker dies. Use at any I/O…
git:20261108.49268da · audit A · 216 stars
find-peers SKILL.md skill
joelhooks/rat-stack · skills/find-peers/SKILL.md · Refresh public peers, exact stack versions, and tiers after stack bumps. On gardener passes, refresh peers checked more…
git:20261027.c3ff8a9 · audit A · 216 stars
gardener SKILL.md skill
joelhooks/rat-stack · skills/gardener/SKILL.md · Keep rat-stack current and clean. Update exact dependency versions, learn from repos on the same versions, and add lint…
git:20261114.31132fb · audit A · 216 stars
investigate-a-failure SKILL.md skill
joelhooks/rat-stack · skills/investigate-a-failure/SKILL.md · Find the cause of a crash, wrong output, flaky test, or slow run with evidence, fix it at its source, and leave a…
git:20261023.b93dadf · audit A · 216 stars

Every file in joelhooks/rat-stack

Browse by kind, by grade A, or by owner.