formal-spec

formal-spec is a skill for Claude Code, Codex from jrjsmrtn/tlx. It costs 86 tokens per session (3,039 once invoked), scanned A, original, MIT.

A workflow for writing and checking formal specifications of state machines with TLX, a way to write TLA+-style specifications in Elixir. It covers describing states and transitions, checking rules, and comparing specifications with implementation code.

In plain words
What is it for?
Use it to specify complex GenServers or state machines, describe safety and liveness rules, check implementation refinements, and add verification to CI.
Why use it?
It helps reveal invalid states, unsafe transitions, and coordination problems that ordinary tests may not cover.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to specify complex GenServers or state machines, describe safety and liveness rules, check implementation refinements, and add verification to CI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jrjsmrtn/tlx/formal-spec
View source ↗ jrjsmrtn/tlx
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 jrjsmrtn/tlx --skill formal-spec
Clone the repo
git clone --depth 1 https://github.com/jrjsmrtn/tlx

Made for: Claude Code, 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 formal-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/jrjsmrtn/tlx/formal-spec/github.svg)](https://agentmods.dev/skills/jrjsmrtn/tlx/formal-spec)
Your own site
<a href="https://agentmods.dev/skills/jrjsmrtn/tlx/formal-spec"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/tlx/formal-spec/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 formal-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/jrjsmrtn/tlx/formal-spec"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/tlx/formal-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,039 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 $0.00086 $0.03039
Opus 5 $0.00043 $0.01520
Sonnet 5 $0.00017 $0.00608
Haiku 4.5 $0.00009 $0.00304

Measured 9d ago against content hash 6688e36b109f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

formal-spec 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 9d 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.

usage-rules/skills/formal-spec/SKILL.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Formal Specification Workflow with TLX

TLX enables formal verification of state machines by writing declarative specs in Elixir and model-checking them with TLC. This skill covers the full lifecycle: design-time abstract specs, implementation-time concrete specs, and CI-time refinement checking.

When to Use This Workflow

Apply formal specification to state machines with:

  • Multiple states and guarded transitions
  • Concurrent access or distributed coordination
  • Safety properties ("this must never happen")
  • Liveness properties ("this must eventually happen")
  • Approval gates, quorum requirements, or sequencing constraints

Not every GenServer needs a spec. Target modules with complex state logic — :gen_statem, GenServers with explicit state machines, or any module where an ADR describes valid/invalid state transitions.

Phase 1: Abstract Spec from ADR

Read the ADR and extract

  1. States — all named states the system can be in
  2. Transitions — which events move between states, with guards
  3. Forbidden transitions — state pairs that must never be directly reachable
  4. Invariants — properties that must hold in every reachable state
  5. Liveness — properties about eventual behavior (optional)

Write the abstract TLX spec

Every spec file starts with a cross-reference header:

# ADR: 0029, 0013
# Source: apps/forge_infra/lib/forge/firmware/orchestrator.ex
  • ADR: — comma-separated ADR numbers this spec derives from
  • Source: — relative path to the implementation (omit for abstract-only specs)
import TLX

defspec AbstractFirmware do
  variable :state, :idle

  action :begin do
    guard(e(state == :idle))
    next :state, :updating
  end

  action :complete do
    guard(e(state == :updating))
    next :state, :committed
  end

  action :fail do
    guard(e(state == :updating))
    next :state, :failed
  end

  invariant :committed_is_terminal,
            e(ite(state == :committed, true, true))
end

Read the full file on GitHub · 401 lines

Files

What ships with it

6 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. 9d ago First seen · 401 lines · 86 tokens per session scan A 6688e36b109f

Subscribe to this mod's changes

formal-spec is a skill published in the GitHub repository jrjsmrtn/tlx (10 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 3,039 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens