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.
npx agentmods add commands/punt-labs/z-spec/partition-devgit 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/partition-dev)<a href="https://agentmods.dev/commands/punt-labs/z-spec/partition-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/partition-dev.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.05360 |
| Opus 5 | $0.00006 | $0.02680 |
| Sonnet 5 | $0.00002 | $0.01072 |
| Haiku 4.5 | $0.00001 | $0.00536 |
Grade A, and why
partition-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- partition — 95% identical, 22 lines differ
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/z-spec-dev:partition-dev - Derive Test Cases from Z Specification
Apply Test Template Framework (TTF) tactics to operation schemas in a Z specification to produce a complete partition table of test cases. Each partition represents a distinct behavioral class that must be tested to verify the implementation conforms to the spec.
Input
Arguments: $ARGUMENTS
Parse arguments:
- First positional argument: Z specification file (default: search
docs/*.tex) --code [language]: Generate executable test code (auto-detect language if omitted)--operation=NAME: Partition a single operation (default: all operations)--json: Output partition data as JSON instead of markdown
Process
0. Prerequisites
This command requires no external tools. It reads an existing
Z specification and applies testing tactics analytically. The specification
should already exist and have been type-checked (via /z-spec-dev:check-dev).
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 - If multiple found, ask user to specify
Read the specification file.
2. Extract Operation Schemas
Scan the specification for operation schemas. An operation schema is
any schema containing \Delta or \Xi:
\begin{schema}{OperationName}
\Delta State \\ % or \Xi State
input? : Type \\ % inputs (optional)
output! : Type % outputs (optional)
\where
% predicates
\end{schema}
For each operation, extract:
- Name: The schema name
- Kind:
\Delta(state-changing) or\Xi(query) - State schema: The referenced state schema name
- Inputs: Variables ending in
?with their types - Outputs: Variables ending in
!with their types - Predicates: All clauses in the
\whereblock
If --operation=NAME is specified, process only that operation.
3. Resolve Context
Before partitioning, resolve the context each operation needs:
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.
- 4d ago First seen · 548 lines · 12 tokens per session scan A 78d4cd504591
partition-dev is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 5,360 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.
Other commands, from other repositories
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
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.