Content
80%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a tight, actionable rule set that trusts Claude's competence and correctly offloads the resolver implementation to bundled scripts. Its main gap is the absence of an explicit verification step before consuming a discovered port, which is the fragile point of this workflow.
Suggestions
Add an explicit validation checkpoint, e.g. after `bun dev:info --json`, verify the returned app URL/port is reachable or non-empty before using it (and retry if the slot env var is unset).
Include a one-line example of the `bun dev:info --json` output shape or a minimal `.worktree-env.json` snippet so the rules have a concrete referent.
Number the bullets (or split into 'Discover' / 'Configure' / 'Run' steps) so the implied sequence is an explicit workflow rather than an unordered list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | A lean bulleted rule set with executable commands and no padding or explanation of concepts Claude already knows; every token earns its place. | 5 / 5 |
Actionability | Concrete commands and files (bun dev:info --json, .env.worktree.local, .worktree-env.json, {apps.<name>.url}) are mostly executable, but no example of the .worktree-env.json shape or dev:info JSON output leaves a minor gap. | 4 / 5 |
Workflow Clarity | The bullets imply a sensible order (run dev:info first, then start via root scripts, configure exports, cross-app templates) but lack any explicit validation checkpoint before using a returned URL or slot. | 3 / 5 |
Progressive Disclosure | The under-50-line body is a clear overview with one well-signaled, one-level-deep reference to the bundled resolver/wrapper in scripts/ (verified to exist). | 5 / 5 |
Total | 17 / 20 Passed |