Bitwarden Server - Claude Code Configuration
## Project Context Files
**Read these files before reviewing to ensure that you fully understand the project and contributing guidelines**
1. `README.md` (read on demand
No other project uses it yet
21k4mo agoReviewMountCreate a free account to mount
file --reason "…"` ONLY to relay
a risk a human has explicitly accepted: a named code-review finding, an ADR, or
the user saying so in this conversation. The --reason must
No other project uses it yet
20k8mo agoReviewMountCreate a free account to mount
Trigger Claude review by commenting `@claude review` on the PR.
3. Address every review comment (`gemini-code-assist`, `coderabbitai`, `claude[bot]`): fix, push, reply on the thread (`Addressed
Steady5 mentions in 2 weeks
No other project uses it yet
20k2mo agoReviewMountCreate a free account to mount
fixes
- Follow existing code style (enforced by ESLint/Prettier)
- Large features need design discussion first
- Codereview required from core contributors
### Important Notes
- This is a monorepo with workspaces: main package
No other project uses it yet
20k7mo agoReviewMountCreate a free account to mount
prompts loaded by Antigravity and other harnesses.
2. `.claude-plugin/agents/`: Contains Claude Code adapters. Reviewer adapters use
`omitClaudeMd: true` and `tools: [Read, Grep, Glob]`; the synthesizer and bootstrap
orchestrator
Steady76 mentions in 2 weeks
No other project uses it yet
20k4d agoReviewMountCreate a free account to mount
multiagent: { type: "coordinator", agents: [...] }` roster so the analyst hands its numbers to a toolless reviewer. The handoff events (`session.thread_created`, `agent.thread_message_sent/received`) already arrive on the stream; the reducer
Steady4 mentions in 2 weeks
No other project uses it yet
19k54d agoReviewMountCreate a free account to mount
else
through `scripts/ops`. Commands that need the user's API credentials (`make
demo`, `make reviewer`, `agentpolicy stop`/`resume`) take `OPS_ANT_PROFILE=1`;
`make dispatcher` never does.
| Symptom | Cause
Steady4 mentions in 2 weeks
No other project uses it yet
19k54d agoReviewMountCreate a free account to mount
asks to turn off a LaunchDarkly flag for the broken code path while the pull request waits for review. Keep it host-side like `open_pull_request`, with the flag
Steady4 mentions in 2 weeks
No other project uses it yet
19k54d agoReviewMountCreate a free account to mount
downstream.
- Every assertion must be capable of failing. An assertion about a condition the code
cannot produce is noise.
- Confirm the test actually runs in CI. Some test files
Steady3 mentions in 2 weeks
No other project uses it yet
18k22mo agoReviewMountCreate a free account to mount
JCache) conformance
When to read which doc:
- Concurrency or thread-safety work → `synchronization.md`
- Reviewingcode → `design-decisions.md` first (prevents false positives); an audit reads it at the auditor's Phase
No other project uses it yet
18k21d agoReviewMountCreate a free account to mount
configs, "Not changed" lists). The code and its tests carry those.
- **A PR may ship with known bugs whose risk is low.** `review-pr` rates each
bug a change introduces
No other project uses it yet
18k10d agoReviewMountCreate a free account to mount
CLAUDE.md
@AGENTS.md
The rest of this file is specific to Claude Code.
## Slash commands
Defined in `.claude/commands/`:
- `/research-issue ` — researches a GitHub issue into `.agent/tasks/ - .md`. Before working on an issue
No other project uses it yet
17k47d agoReviewMountCreate a free account to mount
just apologize — fix the system.
## Evolving preferences
When the user expresses a coding preference, convention, or correction during a session, offer to encode it into this CLAUDE.md file
No other project uses it yet
17k2mo agoReviewMountCreate a free account to mount
code fixtures and `expect-test` snapshots. Follow the nearest existing test helper and fixture convention rather than introducing a new test harness.
- Before planning or writing fixture-based tests, review
No other project uses it yet
17k19mo agoReviewMountCreate a free account to mount
fixed or pinned by a failing test. Never fix only the reproduction a reviewer gave you. If a bug exists in journey X, enumerate every realistic adjacent journey
No other project uses it yet
17k2mo agoReviewMountCreate a free account to mount
APIs. If that fails, you may search the code directly or search the web for more detail.
## Communication Style
When reviewing plans, providing feedback, or analyzing approaches, be genuinely critical
No other project uses it yet
16k5mo agoReviewMountCreate a free account to mount
Extend `BaseMwmFragmentActivity` and override `onSafeCreate()` (not `onCreate()`)
-- ensures C++ core is initialized before activity code runs
- Use `BaseMwmFragment` with `OnBackPressListener` interface
- Thread safety: use `Handler(Looper.getMainLooper())` for UI updates from
Steady2 mentions in 2 weeks
No other project uses it yet
16k7mo agoReviewMountCreate a free account to mount
commit must compile on all platforms and pass tests; exceptions are possible for easier codereview, if PR will be squashed, or for android using string ids before strings regenerated
No other project uses it yet
16k7mo 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.