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.
git clone --depth 1 https://github.com/punt-labs/z-specWrote 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.
[](https://agentmods.dev/commands/punt-labs/z-spec/check-dev)<a href="https://agentmods.dev/commands/punt-labs/z-spec/check-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/check-dev/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.
<a href="https://agentmods.dev/commands/punt-labs/z-spec/check-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/check-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.01035 |
| Opus 5.5 | $0.00003 | $0.00414 |
| Sonnet 5.5 | $0.00001 | $0.00207 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
check-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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- check — 92% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Z Specification with Fuzz
Type-check a Z specification using the fuzz type-checker.
Input
File: $ARGUMENTS
Process
1. Locate the Specification
If a file path is provided, use it directly.
If no file specified:
- Look in
docs/for.texfiles containing Z specifications - Present options if multiple files exist
2. Type-check
Call mcp__plugin_z-spec-dev_zspec__check with file set to the resolved path.
3. Report
The tool returns an object with ok (bool) and errors (list).
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.
ok: true→fuzz: <name> OK.ok: false→fuzz: <name> FAIL, then one line per error, indented two spaces:<line>:<column>: <message>.
The tool has written <stem>.fuzz.json; the show tool renders it
in the Fuzz tab.
4. Animation Readiness Warnings
After a successful fuzz type-check, scan the specification for patterns that pass fuzz but cause probcli animation failures. For each pattern found, emit a warning. Only emit warnings that actually apply to the spec.
Checklist (prefix each with "Animation hint:"):
-
Unbounded
\finsetor\pfun: Any\finset XorX \pfun YwhereXis a given set (declared with[X]syntax, not a free type declared withType ::= ...) and there is no cardinality bound — either a direct\# variable \leq maxBoundconstraint or a domain subset constraint like\dom variable \subseteq boundedSetwhereboundedSetitself has a cardinality bound. Free types are already finite and do not need cardinality bounds. Fix: add an axdef constant and a cardinality constraint, or constrain the domain to a bounded set. -
Cross products for records: Any
\crossused to combine 3+ types (e.g.,X \cross Y \cross Z) where a named schema with fields would be more appropriate. Fix: define a schema with named fields instead. -
Bare-type quantifiers: Any
\forallor\existsthat quantifies over a given type directly (e.g.,\forall n : NAME) instead of over a set from state (e.g.,\forall n : members). Fix: scope the quantifier to the relevant state set.
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.
- 1mo ago First seen · 81 lines · 7 tokens per session scan A e26c51ba24a5
check-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 1,035 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
feedback-to-us
Tell us how the prfaq plugin is working for you (anonymous 1-5 feedback).
badge
Generate a stage-colored badge and embed it in your README.
import
Import an existing document and launch the full /prfaq workflow with extracted content.
research
Research evidence for PR/FAQ claims and generate biblatex citations.
review
Peer review a PR/FAQ document for quality and decision readiness.
streamline
Tighten a PR/FAQ by removing redundancy, weasel words, and bloat.