b-refine-dev

b-refine-dev is a command for coding agents from punt-labs/z-spec. It costs 7 tokens per session (1,368 once invoked), scanned A, original, MIT.

A command for creating or checking a B refinement, which is a more concrete version of an abstract formal specification. It can also produce an implementation version.

In plain words
What is it for?
Use it to generate a .ref file from a .mch B machine, verify an existing refinement, or generate an .imp implementation with the appropriate option.
Why use it?
It helps introduce real data structures while checking that the more detailed design still follows the original specification.

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/b-refine-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.

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 b-refine-dev

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/z-spec/b-refine-dev.svg)](https://agentmods.dev/commands/punt-labs/z-spec/b-refine-dev)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/z-spec/b-refine-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/b-refine-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,368 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 $0.00007 $0.01368
Opus 5 $0.00003 $0.00684
Sonnet 5 $0.00001 $0.00274
Haiku 4.5 $0.00001 $0.00137

Measured 4d ago against content hash 779e6a6761c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

b-refine-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 4d 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:

  • b-refine — 97% identical, 6 lines differ
plugin/commands/b-refine-dev.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/z-spec-dev:b-refine-dev - B Refinement

Create or verify a B refinement machine. B-Method's refinement chain (Machine -> Refinement -> Implementation) lets you introduce concrete data structures while provably preserving the abstract machine's properties.

This command has two modes:

  1. Create mode (one argument): Generate a refinement .ref from an abstract .mch
  2. Verify mode (two arguments): Check that a .ref correctly refines its .mch

Input

Arguments: $ARGUMENTS

Parse arguments:

  • One argument (.mch file): create mode — generate a refinement
  • Two arguments (.mch + .ref): verify mode — check the refinement
  • --imp: Generate an implementation (.imp) instead of a refinement (.ref)

Process

0. Check Prerequisites

Verify probcli is installed:

PROBCLI="${PROBCLI:-$HOME/Applications/ProB/probcli}"
if ! which probcli >/dev/null 2>&1 && [ ! -x "$PROBCLI" ]; then
    echo "PROBCLI_NOT_FOUND"
fi

If probcli not found: Stop and tell the user:

probcli is not installed. Run /z-spec-dev:setup-dev probcli first.

1a. Create Mode

Read the Abstract Machine

Load the .mch file and identify:

  • Machine name
  • SETS (deferred and enumerated)
  • VARIABLES and their types (from INVARIANT)
  • OPERATIONS (names, parameters, preconditions, effects)
  • Key invariants
Guide the Refinement Strategy

Ask the user what data refinement they want. Common strategies:

Abstract Concrete Gluing Invariant
Set Array + count ran(array(1..count)) = abstract_set
Partial function Two parallel arrays !i.(i:1..count => keys(i) |-> vals(i) : abstract_fn)
Sequence Array + length !i.(i:1..length => array(i) = abstract_seq(i))
Enumerated status Integer code status = active <=> code = 1
Unbounded NAT Bounded 0..MAX concrete_val = abstract_val

If the user doesn't specify, suggest the simplest refinement: same data representation with tighter bounds or minor restructuring.

Read the full file on GitHub · 195 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. 4d ago First seen · 195 lines · 7 tokens per session scan A 779e6a6761c9

Subscribe to this mod's changes

b-refine-dev is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 1,368 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.