test-dev

A command for checking and stepping through a Z specification with probcli, the command-line tool from ProB for analysing formal software models. A Z specification is a precise mathematical description of how a system works.

In plain words
What is it for?
Use it to locate a Z file, run its checks, and report the results, with an option for more detailed output and model-checking set sizes.
Why use it?
It catches problems in the specification and shows whether its model can perform valid operations.

Command

Part of the z-spec-dev plugin — 42 commands, 1 hook shipped together

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 commands/punt-labs/z-spec/test-dev
Clone the repo
git clone --depth 1 https://github.com/punt-labs/z-spec

Or install z-spec-dev, the plugin that ships this one along with the rest of its 42 commands, 1 hook.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 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 $0.00009 $0.00924
Opus 5 $0.00005 $0.00462
Sonnet 5 $0.00002 $0.00185
Haiku 4.5 $0.00001 $0.00092

Measured 3d ago against content hash 599b388488f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-dev 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • test — 89% identical, 6 lines differ
plugin/commands/test-dev.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Z Specification with ProB

Validate and animate a Z specification using probcli (ProB command line interface).

Input

Arguments: $ARGUMENTS

Parse arguments:

  • First positional argument: file path (or search in docs/)
  • -v or --verbose: Append each check's detail field to its summary line. Without -v, render only <name>: <status>; with -v, render <name>: <status> — <detail> (display only — the tool returns structured JSON, not raw probcli stdout, so there is no raw output to surface)
  • -s N or --setsize N: Default set size for model checking (default: 2)

-a and -v are not parameters of the test tool. run_full_suite animates a fixed 20 steps internally — custom step counts are the separate animate capability. The tool's max_ops (default 1000) bounds model-checking only, and stays at the default; -v merely changes how this command renders the returned JSON.

Process

1. Locate the Specification

If a file path is provided, use it directly. If no file specified, look in docs/ for .tex files.

2. Verify

Call mcp__plugin_z-spec-dev_zspec__test with file, plus setsize from -s. Leave max_ops and timeout at the tool defaults — they are not wired to flags. -v is the verbose flag (see step 3), not a tool argument.

The tool runs the five checks — parse-and-init, animation, CBC assertions, CBC deadlock, model check — and returns:

{timestamp, probcli_version, setsize, ok, states_analysed,
 transitions_fired, checks:[{name, status, detail}],
 operations:[{name, times_fired, covered}], counter_example?}

It persists <stem>.report.json alongside the spec.

3. Report

If the returned JSON has an error field (e.g. the binary is not installed), show that message to the user and stop — do not render the normal result.

Render the JSON as text. Without -v, render each check as <check.name>: <check.status> (summary only). With -v, append the detail as <check.name>: <check.status> — <check.detail>:

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 9 tokens per session scan A 599b388488f1

Subscribe to this mod's changes

test-dev is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 924 once invoked, about $0.0000 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.