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/elaborate-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/elaborate-dev)<a href="https://agentmods.dev/commands/punt-labs/z-spec/elaborate-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/elaborate-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 | $0.00011 | $0.01611 |
| Opus 5 | $0.00005 | $0.00805 |
| Sonnet 5 | $0.00002 | $0.00322 |
| Haiku 4.5 | $0.00001 | $0.00161 |
Grade A, and why
elaborate-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 5d 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:
- elaborate — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elaborate Z Specification
You are enhancing a formal Z specification by combining it with design documentation to create a polished, readable artifact that serves both as formal specification and design documentation.
Input
Arguments: $ARGUMENTS
Parse arguments as:
- First argument: path to Z specification (
.texfile) - Second argument (optional): path to design documentation (defaults to
DESIGN.md)
Process
1. Read the Specification
Read the Z specification file. Identify:
- Basic types and their intended meaning
- Free types (enumerations)
- State schemas and their fields
- Operations and their purpose
- Any existing narrative text
2. Read Design Documentation
Search for design documentation in order:
- Explicit path from arguments
DESIGN.mdin project rootdocs/DESIGN.mdREADME.md(extract design sections)
Extract relevant content:
- System overview and purpose
- Design philosophy and principles
- Feature descriptions
- Algorithm explanations
- Domain terminology
- Architectural decisions
3. Enhance the Specification
Transform the specification by adding:
Document Structure
\tableofcontents
\newpage
Introduction Section
- System purpose from design docs
- Design philosophy (bullet points)
- Scope of specification (what is/isn't modeled)
Section Narratives
For each major section, add explanatory text:
- Basic Types: Why these given sets? What do they represent?
- Free Types: Domain meaning of each enumeration value
- Constants: Why these values? What do they configure?
- State Schemas:
- What does each field represent?
- Why these invariants matter?
- Semantic meaning (not just type)
- Operations:
- When is this operation used?
- What triggers it?
- Connection to user actions or system events
Algorithm Explanations
Where operations implement algorithms from design docs:
- Add tables summarizing rules (e.g., spaced repetition thresholds)
- Note implementation details not captured in formal model
- Reference design doc sections
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.
- 5d ago First seen · 261 lines · 11 tokens per session scan A 6044640d845f
elaborate-dev is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 1,611 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
research
Research evidence for PR/FAQ claims and generate biblatex citations.
export
Export the PR/FAQ as a Word document (.docx) via pandoc — no TeX installation required.
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.