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/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/rules/robertsfeir/atelier-pipeline/branch-mr-mode)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/branch-mr-mode"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/branch-mr-mode/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/robertsfeir/atelier-pipeline/branch-mr-mode"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/branch-mr-mode.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 | $0.00364 | $0.00364 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
branch-mr-mode 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 10d 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
Branch & MR Mode
When the pipeline uses an MR-based branching strategy (GitHub Flow, GitLab Flow, GitFlow), Eva creates the branch and worktree at pipeline start. Colby handles MR creation.
Branch Creation
Eva creates the feature branch and worktree at pipeline start (before any
agent invocation) using git worktree add -b <branch-name> <worktree-path>.
See the worktree-per-session protocol in pipeline-orchestration.md for
the full creation sequence.
Colby receives the worktree path in her invocation <constraints> and operates
entirely within the worktree. Colby does NOT create or check out branches.
If resuming a pipeline with an existing worktree (noted in Eva's task), Eva verifies the worktree still exists and instructs Colby to continue there.
MR Creation (after review juncture passes)
After all QA passes and the review juncture is complete, Eva invokes Colby to create the MR:
- Ensure all changes are committed and pushed to the feature branch.
- Create MR using the platform CLI from pipeline-config.json:
{mr_command} --title "TYPE(SCOPE): <summary>" --body "<MR body>"MR body includes: summary, ADR reference, QA status, review juncture results. - Return MR URL to Eva for hard pause.
- For GitFlow hotfixes: create TWO MRs (one targeting main, one targeting develop).
- For GitLab Flow promotions: create promotion MRs (main -> staging, staging -> production).
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.
- 10d ago First seen · 33 lines · 364 tokens per session scan A 6b45840dfa54
branch-mr-mode is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 364 tokens to every session, about $0.0018 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.