file paths in `.expected` files
- **Line numbers**: Critical for matching expected warnings to actual code lines
- **Issue types**: Must match exactly (e.g., `PhanTypeInvalidCallableMethodName`)
- **Error messages**: Complete message text must match
Steady4 mentions in 2 weeks
No other project uses it yet
5.6k13mo agoReviewMountCreate a free account to mount
write.
- **Non-tautological tests** — every test must assert behavior that breaks if prod code deleted.
## Layer model and import rules
Three concentric layers. Imports flow inward only.
```
+-------------------------------------------------------------------+
| cmd/router/main.go (composition root
Surging5 mentions in 2 weeks
1 project uses a version of this
5.6k10d agoReviewMountCreate a free account to mount
summary and link to the PR
### Investigating Issues
For older issues, review the state of the code when the issue was raised - it may have already been addressed:
```bash
5.5k30d agoReviewMountCreate a free account to mount
reasoning from the code alone.
- When debugging a failure, start from the incident or issue Polylane recorded: it carries the evidence an investigation already gathered.
- Polylane reviews pull requests
5.5k35d agoReviewMountCreate a free account to mount
issues.
- Validate every finding against the code. Make minimal fixes for confirmed issues within scope, run the relevant checks, then start another blind review with a new subagent under
No other project uses it yet
5.5k8d agoReviewMountCreate a free account to mount
this repository.
## Communication Style
- Be professional, concise, and direct
- Do NOT use emojis in codereviews, changelogs, or any generated content. You may use professional visual indicators or favor markdown
5.4k4mo agoReviewMountCreate a free account to mount
becomes the CHANGELOG entry)
```
This writes a `.changeset/ .md` file — commit it alongside your code. **You never hand-edit `CHANGELOG.md`; Changesets generates it.** If a PR genuinely needs no release
No other project uses it yet
5.4k4mo agoReviewMountCreate a free account to mount
spaces?") — `features/instance-policy/` (`deriveInstancePolicy` in `utils.ts` is the inventory; `getInstancePolicy` from `data.ts` for server code, `loadInstancePolicy` from `loaders.ts` for pages, `useInstancePolicy` from `client.tsx`). When the organization layer lands this becomes
Steady5 mentions in 2 weeks
No other project uses it yet
5.4k9mo agoReviewMountCreate a free account to mount
writing code in that area.
| Document | Read it when |
| --- | --- |
| [docs/conventions/constants.md](docs/conventions/constants.md) | Adding a threshold, interval, ratio, storage key, or any value used twice |
| [docs/conventions/contributing-flow.md](docs/conventions/contributing-flow.md) | Opening, describing, or reviewing
5.3k10mo agoReviewMountCreate a free account to mount
requesting review.
3. Resolve all review comments before merging — do not dismiss without explanation.
---
## CodeReview Standards
### What to Check
1. **Correctness**: Does the code do what it claims
5.2k3mo agoReviewMountCreate a free account to mount
operations; categories alone do not skip tests when running the full suite locally.
### Code Style
```bash
# Check formatting (from src/ directory)
dotnet format --verify-no-changes --severity info --no-restore
5.2k18mo agoReviewMountCreate a free account to mount
turn of the current conversation, you may skip; across sessions, always re-read.
- `.agentic/AGENT_INSTRUCTIONS.md` -- coding conventions, performance rules, operator guidelines, style and formatting.
- `.agentic/SOLUTION_OVERVIEW.md` -- architecture map, dependency flow, task-oriented
Steady2 mentions in 2 weeks
No other project uses it yet
5.2k7mo agoReviewMountCreate a free account to mount
bullet lists of changes; explain review order for large PRs, or omit for small ones
- Disclose PR was authored with AI, include tool name.
## Code Style
- Minimal comments; code should
No other project uses it yet
5.2k6d agoReviewMountCreate a free account to mount
spanning open-source and pro-only code is made in rstudio-pro first: the whole change is
opened as a PR there, reviewed, and approved, but not merged. An "open
5.1k5mo agoReviewMountCreate a free account to mount
AGENTS.md
## Claude Code
- Use plan mode for multi-file, risky, architectural, or ambiguous changes.
- Use subagents only for bounded sidecar work: exploration, review, test triage, or documentation lookup.
- Prefer separate
No other project uses it yet
5.1k5d agoReviewMountCreate a free account to mount
secret**;
values resolve through `@langwatch/secrets` (ADR-132) and `haven env` masks
them. Module code never reads `process.env`.
## Git and GitHub
- Other changes in the checkout belong to someone else. Stage
No other project uses it yet
5k32d agoReviewMountCreate a free account to mount
snapshots if UI changes are intentional: `npm run test -w packages/ui -- -u`
4. **Claude CodeReview After PR Creation**:
- After creating a PR, run `npm run claude:review`
- The command
No other project uses it yet
5k27d agoReviewMountCreate a free account to mount
mocking must be implemented.
**Feature Development (Outside-In Approach — applies to ALL work: planning, reviewing, coding, and auditing)**:
- This is a foundational principle, not just a coding guideline. Apply
5k8mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.