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/testgit clone --depth 1 https://github.com/punt-labs/z-specWhat 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 | $0.00009 | $0.00920 |
| Opus 5 | $0.00005 | $0.00460 |
| Sonnet 5 | $0.00002 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
test 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 3d 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
89% identical to test-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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Z Specification with ProB
Validate and animate a Z specification using probcli (ProB command line interface).
Input
Arguments: $ARGUMENTS
Parse arguments:
- First positional argument: file path (or search in
docs/) -vor--verbose: Append each check'sdetailfield to its summary line. Without-v, render only<name>: <status>; with-v, render<name>: <status> — <detail>(display only — the tool returns structured JSON, not raw probcli stdout, so there is no raw output to surface)-s Nor--setsize N: Default set size for model checking (default: 2)
-a and -v are not parameters of the test tool. run_full_suite
animates a fixed 20 steps internally — custom step counts are the separate
animate capability. The tool's max_ops (default 1000) bounds
model-checking only, and stays at the default; -v merely changes how this
command renders the returned JSON.
Process
1. Locate the Specification
If a file path is provided, use it directly.
If no file specified, look in docs/ for .tex files.
2. Verify
Call mcp__plugin_z-spec_zspec__test with file, plus setsize from -s.
Leave max_ops and timeout at the tool defaults — they are not wired to
flags. -v is the verbose flag (see step 3), not a tool argument.
The tool runs the five checks — parse-and-init, animation, CBC assertions, CBC deadlock, model check — and returns:
{timestamp, probcli_version, setsize, ok, states_analysed,
transitions_fired, checks:[{name, status, detail}],
operations:[{name, times_fired, covered}], counter_example?}
It persists <stem>.report.json alongside the spec.
3. Report
If the returned JSON has an error field (e.g. the binary is not installed),
show that message to the user and stop — do not render the normal result.
Render the JSON as text. Without -v, render each check as
<check.name>: <check.status> (summary only). With -v, append the detail
as <check.name>: <check.status> — <check.detail>:
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.
- 3d ago First seen · 103 lines · 9 tokens per session scan A 56f170296154
test is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 920 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to test-dev, differing in 6 lines, and is treated as a copy.
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.