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/cleanup-devgit 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 | $0.00590 |
| Opus 5 | $0.00003 | $0.00295 |
| Sonnet 5 | $0.00001 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
cleanup-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cleanup — 89% identical, 2 lines differ
What it actually says
Cleanup Z Specification Files
Remove auto-managed TeX tooling files from the project while preserving source specs and PDF output.
Input
Arguments: $ARGUMENTS
- Directory path (default:
docs/)
Files to Remove
TeX tooling (auto-copied by /z-spec-dev:code2model-dev):
fuzz.sty- LaTeX style file*.mf- Metafont source files*.pk- Packed font files*.tfm- TeX font metrics
Build intermediates:
*.aux- LaTeX auxiliary*.log- LaTeX log*.fuzz- fuzz output*.toc- Table of contents
Files to Keep
*.tex- Z specification source files*.pdf- Compiled PDF output
Process
1. Confirm Directory
DOCS_DIR="${1:-docs}"
if [ ! -d "$DOCS_DIR" ]; then
echo "Directory not found: $DOCS_DIR"
exit 1
fi
2. List Files to Remove
Before removing, show what will be deleted:
echo "Files to remove from $DOCS_DIR:"
ls -la "$DOCS_DIR"/fuzz.sty "$DOCS_DIR"/*.mf "$DOCS_DIR"/*.pk "$DOCS_DIR"/*.tfm \
"$DOCS_DIR"/*.aux "$DOCS_DIR"/*.log "$DOCS_DIR"/*.fuzz "$DOCS_DIR"/*.toc 2>/dev/null
3. Remove Files
cd "$DOCS_DIR"
# TeX tooling
rm -f fuzz.sty
rm -f *.mf *.pk *.tfm
# Build intermediates
rm -f *.aux *.log *.fuzz *.toc
4. Report Results
echo ""
echo "Cleanup complete. Remaining files:"
ls -la "$DOCS_DIR"/*.tex "$DOCS_DIR"/*.pdf 2>/dev/null || echo "No .tex or .pdf files"
Output
Report what was removed and what remains:
## Cleanup Complete
Removed from docs/:
- fuzz.sty
- 10 Metafont files (*.mf)
- 3 font files (*.pk, *.tfm)
- 4 build files (*.aux, *.log, *.fuzz, *.toc)
Preserved:
- koch_trainer.tex (source)
- koch_trainer.pdf (output)
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 · 96 lines · 7 tokens per session scan A 459b7bc49ff3
cleanup-dev 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 590 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.