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/disablegit 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 | $0.00007 | $0.00396 |
| Opus 5 | $0.00003 | $0.00198 |
| Sonnet 5 | $0.00001 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
disable 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.
What it actually says
Disable z-spec here
Stop z-spec composing into this repository: its MCP tools decline and it registers no lux menu entries. Nothing it deposited is deleted.
Process
Call mcp__plugin_z-spec_zspec__enablement with action: "disable". It returns
{ok, action, enabled, root, marker, guide, import_line}.
The call is idempotent — disabling a repository that was never enabled is a no-op. It never runs git.
What it changes
| Path | What happens |
|---|---|
CLAUDE.md |
The @.punt-labs/z-spec/CLAUDE.md line is removed |
.punt-labs/z-spec/enabled |
Deleted |
.punt-labs/z-spec/ |
Left in place, dormant — never deleted |
Output
The three paths are where the marker, the guide, and the import line were —
the marker and the line are gone, the guide is dormant. This is what
z-spec disable prints, and the tool returns the same values:
z-spec disabled 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 its removal so the repo stays off for everyone.
If ok is false, either you are outside a git working tree or the repository
refused the write. Report the error verbatim.
Notes
- Disabling does not touch the
z-specCLI, which is never gated. - To turn it back on, run
/z-spec:enable.
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 · 48 lines · 7 tokens per session scan A e698d41abbe0
disable is a command published in the GitHub repository punt-labs/z-spec (5 stars, last pushed 3d ago), licensed MIT. It adds 7 tokens to every session and 396 once invoked, about $0.0000 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
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.