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 rules/robertsfeir/atelier-pipeline/worktree-isolationgit 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/worktree-isolation)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/worktree-isolation"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/worktree-isolation.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 | $0.01189 | $0.01189 |
| Opus 5 | $0.00594 | $0.00594 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
worktree-isolation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree-Per-Session Isolation
JIT-loaded reference. Extracted from pipeline-orchestration.md. Eva loads
this file on demand when a pipeline session needs worktree creation,
cleanup, or Agent-Teams branching details. The <protocol id="worktree-per-session">
anchor is preserved for downstream references.
Worktree-Per-Session Isolation (ADR-0038)
Every pipeline session gets a dedicated git worktree, regardless of sizing. Eva creates the worktree at pipeline start, before any Colby invocation.
Creation Sequence
After sizing decision and branch name determination, Eva runs:
# 1. Generate session ID (8 hex chars)
SESSION_ID=$(openssl rand -hex 4)
# 2. Determine branch name
# Micro/Small: session/<session-id>
# Medium/Large: feature/<adr-slug>-<session-id>
BRANCH_NAME="session/${SESSION_ID}" # or feature/<slug>-${SESSION_ID}
# 3. Determine worktree path (sibling directory, NOT inside repo)
PROJECT_SLUG=$(basename "$(git remote get-url origin 2>/dev/null)" .git 2>/dev/null || basename "$PWD")
WORKTREE_PATH="../${PROJECT_SLUG}-${SESSION_ID}"
# 4. Create worktree with new branch
git worktree add -b "$BRANCH_NAME" "$WORKTREE_PATH"
# 5. Copy gitignored config (brain-config.json)
if [ -f ".claude/brain-config.json" ]; then
cp ".claude/brain-config.json" "${WORKTREE_PATH}/.claude/brain-config.json"
fi
Branch naming table:
| Pipeline Sizing | Branch Prefix | Merge Strategy |
|---|---|---|
| Micro | session/<8-hex> |
Fast-forward to main |
| Small | session/<8-hex> |
Fast-forward to main |
| Medium | feature/<adr-slug>-<8-hex> |
MR/PR flow |
| Large | feature/<adr-slug>-<8-hex> |
MR/PR flow |
Worktree creation is not conditional — Micro and Small sessions create session branches and dedicated worktrees exactly as Medium and Large do.
Failure Handling
If git worktree add fails (branch name conflict, disk full, permissions),
Eva announces the error verbatim and does NOT proceed to Colby. The pipeline
is a blocker. The user resolves the issue (delete stale worktree, choose
different branch name) and retries. No silent fallback to in-place operation.
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.
- 5d ago First seen · 124 lines · 1,189 tokens per session scan A 0c8203e3d9c9
worktree-isolation is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,189 tokens to every session, about $0.0059 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
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.
family-instance-domain-actions
Family instance domain action implementation 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.