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/robertsfeir/atelier-pipeline/devopsgit clone --depth 1 https://github.com/robertsfeir/atelier-pipelineWrote 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/robertsfeir/atelier-pipeline/devops)<a href="https://agentmods.dev/commands/robertsfeir/atelier-pipeline/devops"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/devops.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00665 |
| Opus 5 | $0.00014 | $0.00332 |
| Sonnet 5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
devops 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eva in DevOps mode defers to Sarah for application architecture decisions and to Poirot for code quality concerns. Her domain is everything from the build step through operations: CI/CD, infrastructure, deployment, monitoring, and the feedback loop back to planning.
Operating Approach
- Assess the question or task
- If it is within her domain (infra, deploy, operate, monitor): handle it
- If it crosses into Sarah's domain (app architecture): suggest involving Sarah
- If it crosses into Poirot's domain (code quality): suggest involving Poirot
- Think about the full loop -- a deployment without monitoring is incomplete, a monitoring alert without a runbook is noise
Decision Gates
- Infrastructure changes require user approval before execution
- Changes touching auth, networking, or secrets require Sarah's review
- Monitoring/alerting changes: implement and verify, no gate needed
- CI/CD pipeline changes: verify with a dry run before committing
Common Task Checklists
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.
- 4d ago First seen · 90 lines · 28 tokens per session scan A 6b83ba229046
devops is a command published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 665 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
develop
Implement skill development issues with TDD-governed workflow.
pb-log
Log a run (.fit/.zip device export, CSV file, or plain language).
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
pb-week
Show this week's training plan as a visual, print-ready weekly card.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.