spec-audit

spec-audit is a skill for Claude Code, Codex from jrjsmrtn/tlx. It costs 88 tokens per session (1,278 once invoked), scanned A, original, MIT.

A project audit for TLX formal specifications, which are precise descriptions that can be checked against code. It finds Elixir and Erlang modules whose state or workflow can be formally described and reports existing coverage.

In plain words
What is it for?
Use it before starting verification, after adding modules, or before a release to review coverage across GenServers, state machines, Phoenix LiveViews, Ash state machines, Reactor, and Broadway workflows.
Why use it?
It shows where formal checks already exist and helps you decide which unverified modules deserve attention first.

Skill for Claude CodeCodex

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

Good fit Use it before starting verification, after adding modules, or before a release to review coverage across GenServers, state machines, Phoenix LiveViews, Ash state machines, Reactor, and Broadway workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jrjsmrtn/tlx/spec-audit
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 spec-audit
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 spec-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/jrjsmrtn/tlx/spec-audit.svg)](https://agentmods.dev/skills/jrjsmrtn/tlx/spec-audit)
Your own site
<a href="https://agentmods.dev/skills/jrjsmrtn/tlx/spec-audit"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/tlx/spec-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,278 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 $0.00088 $0.01278
Opus 5 $0.00044 $0.00639
Sonnet 5 $0.00018 $0.00256
Haiku 4.5 $0.00009 $0.00128

Measured 8d ago against content hash 9b9c5c751765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-audit 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 8d 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/spec-audit/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Audit — Formal Verification Coverage Report

Scan a project to find modules that TLX extractors can process, check which already have formal specs, and prioritize verification effort.

When to Use

  • Starting formal verification on an existing project
  • After adding new modules and wondering if they need specs
  • Reviewing spec coverage before a release
  • Triaging which modules to formally specify first

Step 1: Scan for Extractable Modules

Search the project's lib/ directory for modules matching these patterns:

OTP Behaviours

Pattern Type Extractor
use GenServer or @behaviour :gen_server GenServer mix tlx.gen.from_gen_server
use GenStateMachine or @behaviour :gen_statem gen_statem mix tlx.gen.from_state_machine
use Phoenix.LiveView LiveView mix tlx.gen.from_live_view
.erl with -behaviour(gen_server) Erlang gen_server mix tlx.gen.from_erlang
.erl with -behaviour(gen_fsm) Erlang gen_fsm mix tlx.gen.from_erlang

Framework Extensions

Pattern Type Extractor
extensions: [AshStateMachine] Ash.StateMachine mix tlx.gen.from_ash_state_machine

Workflow & Pipeline Libraries

Pattern Type Extractor
use Reactor Reactor workflow mix tlx.gen.from_reactor
use Broadway Broadway pipeline mix tlx.gen.from_broadway

Scan commands

# OTP behaviours
grep -rl "use GenServer\|@behaviour :gen_server" lib/
grep -rl "use GenStateMachine\|@behaviour :gen_statem" lib/
grep -rl "use Phoenix.LiveView\|use.*Live" lib/
grep -rl "behaviour(gen_server)\|behaviour(gen_fsm)" lib/ --include="*.erl"

# Framework extensions
grep -rl "AshStateMachine" lib/

# Workflow & pipeline
grep -rl "use Reactor" lib/
grep -rl "use Broadway" lib/

Step 2: Check Existing Spec Coverage

For each extractable module, check if a corresponding spec exists:

Read the full file on GitHub · 135 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. 8d ago First seen · 135 lines · 88 tokens per session scan A 9b9c5c751765

Subscribe to this mod's changes

spec-audit is a skill published in the GitHub repository jrjsmrtn/tlx (10 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,278 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.