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/plugins/punt-labs/z-spec/plugin)<a href="https://agentmods.dev/plugins/punt-labs/z-spec/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/z-spec/plugin/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/plugins/punt-labs/z-spec/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/z-spec/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
z-spec-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.
What it actually says
{
"name": "z-spec-dev",
"description": "Create, validate, and test formal Z specifications for stateful systems using fuzz and probcli",
"version": "0.20.5",
"author": {
"name": "Punt Labs",
"email": "[email protected]"
},
"mcpServers": {
"zspec": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--directory",
"${CLAUDE_PLUGIN_ROOT}",
"z-spec",
"mcp"
],
"env": {
"ZSPEC_PLUGIN_ROOT": "${CLAUDE_PLUGIN_ROOT}",
"CLAUDE_PROJECT_DIR": "${CLAUDE_PROJECT_DIR}"
}
}
}
}
What it installs
The manifest is a name and a version. 42 commands, 1 hook travel with it, and installing the plugin installs all of them — 400 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command oracle-dev A 12 tokens
- Command refine A 14 tokens
- Command refine-dev A 14 tokens
- Command setup A 11 tokens
- Command setup-dev A 11 tokens
- Command contracts-dev A 17 tokens
- Command code2model-dev A 11 tokens
- Command partition-dev A 12 tokens
- Command prove A 10 tokens
- Command prove-dev A 10 tokens
- Command audit-dev A 7 tokens
- Command elaborate-dev A 11 tokens
- Command model2code-dev A 6 tokens
- Command b-create-dev A 12 tokens
- Command b-refine-dev A 7 tokens
- Command b-animate-dev A 10 tokens
- Command check-dev A 7 tokens
- Command test-dev A 9 tokens
- Command b-check-dev A 8 tokens
- Command cleanup-dev A 7 tokens
- Command disable A 7 tokens
- Command disable-dev A 7 tokens
- Command enable-dev A 7 tokens
- Command help A 10 tokens
- Command help-dev A 10 tokens
- Command doctor B 5 tokens
- Command doctor-dev B 5 tokens
- Command oracle A 12 tokens
- Command audit A 7 tokens
- Command test A 9 tokens
- Command cleanup A 7 tokens
- Command partition A 12 tokens
- Command check A 7 tokens
- Command b-create A 12 tokens
- Command enable A 7 tokens
- Command contracts A 17 tokens
- Command code2model A 11 tokens
- Command b-animate A 10 tokens
- Command b-check A 8 tokens
- Command b-refine A 7 tokens
- Command model2code A 6 tokens
- Command elaborate A 11 tokens
- Hook PostToolUse A not measured
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 Changed f517ad299edb
- 1mo ago First seen · 27 lines scan A c20b5f703b87
z-spec-dev is a plugin published in the GitHub repository punt-labs/z-spec (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
prfaq-dev
Amazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
dev-loop
Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed workerdone / question / escalation events instead of polling, st.
vox-dev
Text-to-speech for Claude Code: /unmute, /mute, /vibe, /vox:recap.
harnessay
Profile Claude Code and Codex transcripts: context budget reports, before/after comparisons, source evidence, and skill regression tests. Local-only, stdlib-only.
xcode-cli
Xcode CLI — Build, test, run, and manage Xcode projects from Claude Code.