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/enable)<a href="https://agentmods.dev/commands/punt-labs/z-spec/enable"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/enable/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/enable"><img src="https://agentmods.dev/badge/commands/punt-labs/z-spec/enable.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 | $0.00450 |
| Opus 5.5 | $0.00003 | $0.00180 |
| Sonnet 5.5 | $0.00001 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
enable 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.
This is a copy
91% identical to enable-dev — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Enable z-spec here
z-spec is per-repo. Its MCP tools and its lux menu entries are live only where
someone ran enable and committed .punt-labs/z-spec/enabled. Run this once per
repository that does formal Z work.
Process
Call mcp__plugin_z-spec_zspec__enablement with action: "enable". It returns
{ok, action, enabled, root, marker, guide, import_line}.
The call is idempotent, and re-running it is the upgrade path — it redeposits
the shipped guide, adds the @-import line only if absent, and rewrites the
marker. It never runs git.
What it writes
| Path | Why |
|---|---|
.punt-labs/z-spec/CLAUDE.md |
The z-spec agent guide, overwritten wholesale |
.punt-labs/z-spec/enabled |
The marker every z-spec MCP tool reads |
CLAUDE.md |
One bare line: @.punt-labs/z-spec/CLAUDE.md |
Output
Report the three paths, then the one action left for the human. This is what
z-spec enable prints, and the tool returns the same values:
z-spec enabled in /repo
marker: /repo/.punt-labs/z-spec/enabled
guide: /repo/.punt-labs/z-spec/CLAUDE.md
import: @.punt-labs/z-spec/CLAUDE.md
Commit the marker so enablement travels with the repo.
If ok is false, either you are outside a git working tree or the repository
refused the write. Report the error verbatim; do not create a repository.
Notes
- The
z-specCLI is never gated.z-spec checkand friends work from a terminal whether or not the marker exists. - To turn it off again, run
/z-spec:disable.
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 · 50 lines · 7 tokens per session scan A 329fa87be9ae
enable 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 450 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to enable-dev, differing in 6 lines, and is treated as a copy.
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.