Borrowing it
Nothing to install: this file belongs to comet-ml/opik-mcp. 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/comet-ml/opik-mcp/main/.claude/commands/create-pr.mdgit clone --depth 1 https://github.com/comet-ml/opik-mcpWrote 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/comet-ml/opik-mcp/create-pr)<a href="https://agentmods.dev/commands/comet-ml/opik-mcp/create-pr"><img src="https://agentmods.dev/badge/commands/comet-ml/opik-mcp/create-pr/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/comet-ml/opik-mcp/create-pr"><img src="https://agentmods.dev/badge/commands/comet-ml/opik-mcp/create-pr.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 | $0.00028 | $0.00647 |
| Opus 5.5 | $0.00011 | $0.00259 |
| Sonnet 5.5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
create-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 23d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a draft PR for the current branch in comet-ml/opik-mcp. Re-run every
step each time; never skip one because an earlier run passed.
1. Preflight
gh auth status. If not logged in, stop and tell me to rungh auth login.- Not on
main. Take the ticket key from the branch name (OPIK-1234). - If
gh pr list --head <branch> --state openfinds a PR, ask whether to update its body or stop.
2. Commit and push
- Tracked changes: stage and commit them in the style of
.claude/rules/git-workflow.md. - Untracked files: list them and ask which to add. Never
git add -A. git fetch origin main. If the branch is behind, say by how many commits and ask. Don't rebase or force-push yourself.git push -u origin HEAD.
3. Checks
- Use the
test-runnersubagent to run all three CI targets:make check,make hermetic,make skills-verify-source. If one fails, show the failures and ask whether to stop or open the PR anyway, marked in the Testing section. - Use the
code-reviewersubagent on the branch. Show me Critical and High findings and ask before continuing.
4. Body
Fill .github/pull_request_template.md. Short bullets, plain words.
- Title:
[OPIK-XXXX] <what changed>, about 60 characters. - Details: what changed for the user or the agent, then anything the reviewer should look at first. Include the context cost if the change adds any (surface bytes before → after, from the budget test).
- Issues:
Resolves OPIK-XXXX. Related tickets asOPIK_1234. - AI-WATERMARK: fill it honestly.
AI-WATERMARK: yes - Tools: Claude Code - Model(s): <the model you are running as> - Scope: <full implementation | assisted | review only> - Human verification: <what the developer checked; ask me if unsure> - Testing: the three targets and their counts, plus
/dogfoodif it was run. - No customer or workspace names, internal hosts or secrets. The repo is public.
End the body with the attribution line from the session instructions, if there is one.
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.
- 23d ago Changed 5158b89a7cb2
- 24d ago First seen · 63 lines · 28 tokens per session scan A 88578beab8a9
create-pr is a command published in the GitHub repository comet-ml/opik-mcp (223 stars, last pushed 2d ago), licensed Apache-2.0. It adds 28 tokens to every session and 647 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-25.
Other commands, from other repositories
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
autotask
Execute development task autonomously from description to PR-ready - handles implementation, testing, and git workflow without supervision.
test
Test commit. Use for add tests, update tests, test coverage, unit test, spec.
check-fix
Execute quality gates, fix any issues found, and create a single high-quality Conventional Commit summarizing all changes made.
test-audit
Writes a versioned TESTAUDIT.md; with --fix, quarantines the rot in gated, revertible commits. TRIGGER WHEN: auditing a test suite, measuring test health, finding dead or flaky or redundant tests, or diagnosing failure causes and proposing temporary quarantine. DO NOT TRIGGER WHEN: one module's tests are consolidated…
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.