Opik is an open-source platform for tracing, evaluating, and monitoring applications that use large language models, retrieval systems, or AI agents. Teams use it to inspect agent activity, manage prompts, run evaluations, and monitor these applications in production.
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.
git clone --depth 1 https://github.com/comet-ml/opikWrote 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/rules/comet-ml/opik/git-workflow)<a href="https://agentmods.dev/rules/comet-ml/opik/git-workflow"><img src="https://agentmods.dev/badge/rules/comet-ml/opik/git-workflow/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/rules/comet-ml/opik/git-workflow"><img src="https://agentmods.dev/badge/rules/comet-ml/opik/git-workflow.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 | $0.01009 | $0.01009 |
| Opus 5.5 | $0.00404 | $0.00404 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
git-workflow 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Branch Naming
{username}/{ticket}-{summary}
andrescrz/OPIK-2180-add-featureuser/issue-123-fix-buguser/NA-hotfix-description
Commit Format
First commit in branch (used as PR title source):
[<TICKET-KEY>] [COMPONENT] <type>: description
[OPIK-1234] [BE] feat: add create trace endpoint[issue-123] [FE] fix: guard empty state[NA] [DOCS] docs: update API documentation
Follow-up commits (preferred):
<type>(<scope>): description
feat(metrics): add project chart filtersfix(api): handle null feedback scoretest(backend): cover trace creation
Revision N: ... is a last-resort fallback only.
PR Title
[<TICKET-KEY>] [COMPONENT] <type>: description
PR Body
Follow .github/pull_request_template.md — read the FULL template file before drafting.
CI (pr-lint) fails the PR if any of these exact headings is missing:
## Details, ## Change checklist, ## Issues, ## Testing, ## Documentation.
Fill in ## AI-WATERMARK too (Tools, Model(s), Scope, Human verification).
Never substitute your own structure (e.g. ## Summary / ## Test Plan).
A section that does not apply gets N/A — never delete a heading.
## Details — style
Write what changes for a user. A reviewer reads the diff for the code; this section tells them what is different when they use the product.
- Short. Most PRs need 3–10 bullets. If it runs longer, the section is doing the diff's job — cut it.
- Bullets, not prose paragraphs. One behavior per bullet. Nest one level for sub-cases.
- Authoritative. State what happens: "The run is scored once." Not "This should now mean that the run will be scored once."
- No fluff. No motivation paragraph, no "this PR …", no approach summary, no benefits list, no restating the diff.
- Observable behavior first. What the UI shows, what the API returns, what gets scored, stored or logged. Name a class, method or file only when the behavior makes no sense without it.
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.
- 1mo ago Changed · +30 lines · +410 tokens per session c5d91272854e
- 1mo ago First seen · 47 lines · 599 tokens per session scan A 2a977074bfa6
git-workflow is a cursor rule published in the GitHub repository comet-ml/opik (22,699 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,009 tokens to every session, about $0.0040 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 2026-08-30.
Other cursor rules, from other repositories
git
Git commit, branch, and PR conventions for this repository.
commit
Commit rules — branch safety, explicit staging, 3-option commit messages, push approval.
no-ai-contributors
Never add AI tools as git authors or project contributors.
git-discipline
Commit, push, and branching rules. Owns ALL git behavior; other files state only their deviations.
git-commit-standards
Enforce structured Git commit messages.
git
Cursor rule "git" from duongductrong/cursor-kit, covering git conventions, commit messages, types, subject rules and examples.