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/zenml-io/zenml/prgit clone --depth 1 https://github.com/zenml-io/zenmlWhat 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 | $0.00011 | $0.00265 |
| Opus 5 | $0.00005 | $0.00133 |
| Sonnet 5 | $0.00002 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
pr 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 2d 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
Prepare and create pull request
First, let me run the formatting script:
! bash scripts/format.sh
Now let me check what files were modified:
! git status --short
Let me also check if there's a CLAUDE.md with PR instructions:
@CLAUDE.md
Steps to create PR:
- Review the changed files listed above and determine which ones are related to our current work
- Stage only the relevant files - I'll ask you to confirm which files to stage if there are unrelated changes
- Determine the base branch:
- If you provided an argument: use
$1 - Otherwise, I'll ask you to confirm if it should be
develop(the usual default) or another branch
- If you provided an argument: use
- Create the PR using the
ghCLI tool according to any instructions in CLAUDE.md - Ask you for:
- PR title (if not obvious from the changes)
- PR description (I'll draft one based on the changes)
Let's proceed! Based on the git status above, which files should we stage for this PR?
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.
- 2d ago First seen · 35 lines · 11 tokens per session scan A fcc3508f9745
pr is a command published in the GitHub repository zenml-io/zenml (5,572 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 265 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
pre-pr
Run the full OpsML test suite (Rust + Python) before submitting a PR. Capture and report all errors clearly at each step. Stop a workflow only if a step produces errors that would block the next step from running correctly.
qa-testing-feature
Run QA testing on the current branch's feature.
run-engine-tests
Fast local test loop for the engine package.
ds-brief
Rewrite the results as a one-page brief with no jargon.
ds-deploy
Serve a packaged model with monitoring, drift detection, and rollback.
ds-iterate
Diagnose what the evaluation found and route back to the stage that fixes it.