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.
/plugin marketplace add punt-labs/z-specnpx agentmods add plugins/punt-labs/z-spec/plugingit clone --depth 1 https://github.com/punt-labs/z-specGrade 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 yesterday.
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": "0.20.4",
"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 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.
- yesterday 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.
paperjury
Pre-submission AI review and editing for CS-conference papers: direct-edit LaTeX or Markdown (Word via one-time extraction), run an adversarial multi-agent courtroom review with consensus-gated revisions, or run it unattended toward a goal.
humanizer
Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's "Signs of AI writing" guide.
polygraph
Plugin marketplace listing 2 plugins: polygraph, polyviz.
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…
quarry-dev
Local semantic search for Claude Code: /find, /ingest, /remember, /explain, /source, /quarry.