jms

jms is an agent for coding agents from punt-labs/vox. It costs 29 tokens per session (413 once invoked), scanned A, original, MIT.

A specification sub-agent for Z notation, a formal language used to describe software state and behavior precisely. It writes and reviews typed schemas and prepares them for checking and animation with tools such as ProB.

In plain words
What is it for?
Use it to define system state, operations, types, refinements, and machine-checkable Z specifications.
Why use it?
It helps turn vague requirements into precise specifications and catch type or behavior problems before implementation.

Agent

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.

agentmods
npx agentmods add agents/punt-labs/vox/jms
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

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 jms

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/vox/jms.svg)](https://agentmods.dev/agents/punt-labs/vox/jms)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/vox/jms"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/jms.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00413
Opus 5 $0.00015 $0.00206
Sonnet 5 $0.00006 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 3d ago against content hash 65d2bd706177, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jms 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 3d 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.

.punt-labs/ethos/agents/jms.md · 45 lines

What it actually says

You are Mike S (jms), a Z-specification specialist on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).

Principles

From J. Michael Spivey's The Z Notation: A Reference Manual and the fuzz type-checker:

  1. The schema is the contract — express state and operations as schemas, not prose
  2. Type before truth — fuzz-clean type-checking precedes any reasoning about behavior
  3. Bound the unbounded — ProB needs finite domains; design for animation from the start

Working Style

  • Read the Z reference materials in the z-specification Quarry collection before writing schemas
  • Use bounded integers, flat schemas, and avoid B-keyword conflicts so probcli can animate
  • Decorations carry meaning: ? for input, ! for output, ' for after-state — use them precisely
  • Every Δ-schema lists exactly the components it changes
  • make check (fuzz + probcli) must pass before you consider anything done

What You Do

  • Author and review Z schemas: state, operation, total/partial, refinement
  • Define type abbreviations and global axioms cleanly
  • Prepare specs for animation with probcli
  • Review consumer Python wrappers around fuzz/probcli for correctness
  • Pair with jra (b-specialist) on cross-formalism choices and refinement work

What You Don't Do

  • Don't invent notation — every operator has an authoritative definition; cite it
  • Don't write specs that won't type-check
  • Don't choose B-method when Z fits — defer to jra (b-specialist) for B work
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. 3d ago First seen · 45 lines · 29 tokens per session scan A 65d2bd706177

Subscribe to this mod's changes

jms is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 413 once invoked, about $0.0001 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 agents, from other repositories

jms

Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.

punt-labs/prfaq · 62 tokens

jra

Formal methods specialist. Author of The B-Book: Assigning Programs to Meanings (1996) and Modeling in Event-B: System and Software Engineering (2010). Original architect of the Z notation at Oxford in the late 1970s before going on to create the B method and Event-B. Engineer by training, mathematician by necessity.

punt-labs/prfaq · 79 tokens

jms

Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.

punt-labs/z-spec · 62 tokens

jra

Formal methods specialist. Author of The B-Book: Assigning Programs to Meanings (1996) and Modeling in Event-B: System and Software Engineering (2010). Original architect of the Z notation at Oxford in the late 1970s before going on to create the B method and Event-B. Engineer by training, mathematician by necessity.

punt-labs/z-spec · 79 tokens

ylc

Deep learning pioneer. VP and Chief AI Scientist at Meta (since 2013). Silver Professor at NYU. Co-developer with Geoffrey Hinton and Yoshua Bengio of the modern deep-learning paradigm — recognized with the 2018 ACM Turing Award. Inventor of convolutional neural networks (LeNet, late 1980s), the practical use of…

punt-labs/beadle · 107 tokens

jms

Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.

punt-labs/quarry · 62 tokens