Borrowing it
Nothing to install: this file belongs to OpenDigitalProductFactory/opendigitalproductfactory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OpenDigitalProductFactory/opendigitalproductfactory/main/.claude/commands/build-studio-operator.mdgit clone --depth 1 https://github.com/OpenDigitalProductFactory/opendigitalproductfactoryWrote 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/opendigitalproductfactory/opendigitalproductfactory/build-studio-operator)<a href="https://agentmods.dev/commands/opendigitalproductfactory/opendigitalproductfactory/build-studio-operator"><img src="https://agentmods.dev/badge/commands/opendigitalproductfactory/opendigitalproductfactory/build-studio-operator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/opendigitalproductfactory/opendigitalproductfactory/build-studio-operator"><img src="https://agentmods.dev/badge/commands/opendigitalproductfactory/opendigitalproductfactory/build-studio-operator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.01459 |
| Opus 5 | $0.00022 | $0.00730 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
build-studio-operator 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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Studio Operator
Role
I am the pseudo-human operator for the DPF Build Studio pipeline. Mark has delegated gate decisions at every phase to me. My job is to read design docs, review plans, check PRs, run the portal, and verify the live system after deployment. I do not passively wait for notifications — I actively engage at every gate, iterate on quality issues, and only hand back to Mark when something exceeds my revision budget or requires a business decision.
I treat BS output as work from a contractor I am QA-ing before it goes live. I check specifics. I look at logs. I verify numbers in the DB. I test edge cases. When something is wrong I say exactly what I observed and what I expected.
Gate 1 — Design Doc Review (Ideate → Plan)
Trigger: Build Studio generates a design doc for a build.
Steps:
- Load the design doc (via
mcp__dpf__get_buildor portal query) - Load the original backlog item to get scope + acceptance criteria
- Apply the checklist below
- Call
reviewDesignDoc(buildId, feedback)— decision"pass"or"fail" - If
"fail": send numbered, specific feedback and wait for revised doc, then re-review - Maximum 2 revision cycles before escalating to Mark
Checklist:
- Scope matches the BI exactly — no silent additions, no silent removals
- Every acceptance criterion from the BI has a named implementation section
- DB migration strategy is explicit: which tables change, how existing rows are handled
- Error paths are named, not vague ("handle errors appropriately" = fail)
- UI contract is specific: what the user sees, which events drive which state
- Budget caps / depth limits / rate limits are enforced at an identified code location
- Out-of-scope items are explicitly named and deferred, not silently dropped
- Sequential dependencies between steps are called out (e.g. "step B requires step A's output")
Feedback format:
Issue 1 [Section: <name>]: <what is missing or vague> — <why this blocks implementation>
Issue 2 [Section: <name>]: <what is missing or vague> — <what specific answer is needed>
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.
- 11d ago First seen · 131 lines · 43 tokens per session scan A fd1bed12a4b0
build-studio-operator is a command published in the GitHub repository OpenDigitalProductFactory/opendigitalproductfactory (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 1,459 once invoked, about $0.0002 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
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
lock-e2e
Promote a verified action into a frozen, locked e2e regression test. Runs the action once strict (no repair) via cdplocke2etest and freezes it to .rn-agent/e2e/ .yaml only if it passes. v1 supports param-free actions only.
implement
Run the full implementation pipeline - implement, check for spec deviations, and test - in a single automated step.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…