limited to, interactions such as pushing code, opening issues or pull requests, and replying to issues, pull requests, or reviews.
- The user is required to disclose your agent information (harness
No other project uses it yet
51k1d agoReviewMountCreate a free account to mount
MODEL_VERSION [TOOL1] [TOOL2]`.
- **The human submitter is responsible** for reviewing, testing, and understanding every line of generated code.
## Topics
| File | When to read |
|------|-------------|
| [.agents/ai-coding-assistants.md](.agents/ai-coding-assistants.md) | Policy for AI-assisted
Steady3 mentions in 2 weeks
No other project uses it yet
50k3y agoReviewMountCreate a free account to mount
changelog for breaking API changes.
# Skills
For detailed guidance on writing and reviewingcode and documentation, see the skills in [.claude/skills/](.claude/skills/):
## Clojure
### clojure-mcp tools
- **[clojure-eval](.claude/skills/clojure-eval/SKILL.md)** - Always
No other project uses it yet
50k7d agoReviewMountCreate a free account to mount
last_review_date: "2026-06-10"
---
# Agent Instructions for Homebrew/brew docs
These instructions apply when working in `docs/`.
## Tooling
- Use the system Homebrew `brew bundle exec ...` workflow from this directory
No other project uses it yet
50k2mo agoReviewMountCreate a free account to mount
self-contained PRs that are easier to understand and review.
### Size Limits
- **Lines changed**: Keep PRs under 500 lines of code (additions + deletions)
- **Files changed**: Keep PRs under 10 code
1 project uses a version of this
50k20d agoReviewMountCreate a free account to mount
package (`gitnexus/skills/`, installed to editor targets
by `gitnexus setup`) and the Claude Code plugin; review also has a standalone Cursor
mirror. `gitnexus/test/unit/shipped-skills-sync.test.ts` guards the copies. Token savings of the workflow
Steady31 mentions in 2 weeks
No other project uses it yet
49k2mo agoReviewMountCreate a free account to mount
before investing in implementation and review.
- Issue reports must describe observed behavior, reproduction steps, and relevant logs. Do not add speculative root causes, code analysis, or proposed fixes to agent
No other project uses it yet
48k5d agoReviewMountCreate a free account to mount
incompetent you are. Do it right on your first try, fact-check and review after changes. If you are not sure, ask for help.
- When you see changes made outside
No other project uses it yet
48k5mo agoReviewMountCreate a free account to mount
standalone
runtime smoke test must remain executable on Node 8, and generated library code
must continue to pass the runtime compatibility workflow.
Moment has no runtime dependencies
No other project uses it yet
48k3mo agoReviewMountCreate a free account to mount
selected project in the monorepo with only dependencies that it has
## Security Model
When reviewingcode, writing security documentation, or performing security research, keep in
mind the following aspects
No other project uses it yet
47k5d agoReviewMountCreate a free account to mount
When reviewing provider PRs
Flag any of these patterns:
- `**conn.extra_dejson` or `**self.extra_dejson` spread into a constructor
or call.
- Looping over `conn.extra_dejson.items()` and forwarding every key.
- New code paths
No other project uses it yet
47k5d agoReviewMountCreate a free account to mount
maintenance
- **Final frontend checks:** After frontend code changes, run `pnpm run lint` in `app/` (types, auto-fixing ESLint, CSS/menu/startup-language checks, not behavioral tests). Review its diff, keeping fixes in scope
No other project uses it yet
47k8d agoReviewMountCreate a free account to mount
already split into state, actions, and input. Keep it that way.
- **Platform code is isolated.** OS-specific behavior lives in the matching `src/platform/ .rs` file, with only shared traits, types
1 project uses a version of this
47k2mo agoReviewMountCreate a free account to mount
Keep only what the change carries, and describe
the code as it stands rather than narrating earlier commits or review rounds. Naming the merged
pull request that caused
1 project uses a version of this
47k3mo agoReviewMountCreate a free account to mount
being implemented, or where direct package-manager behavior is required.
# Background Work
- Long-running code (the shell, daemons, watchers) reacts to events instead of polling with a timer. Polling
Steady13 mentions in 2 weeks
1 project uses a version of this
47k2mo agoReviewMountCreate a free account to mount
commit, push, or publish merely because implementation is complete.
For PR review, use [code-review](.github/skills/code-review/SKILL.md).
For sandboxed reproductions with `ghmock`, use [ghmock](.github/skills/ghmock/SKILL.md).
For authorized maintainer debt maintenance
No other project uses it yet
47k55d agoReviewMountCreate a free account to mount
Review Comments**: Before requesting re-review, ensure all previous review comments are addressed, not just some of them.
### Code Organization
45. **Move Functions Up**: Move function definitions to the highest
Steady4 mentions in 2 weeks
No other project uses it yet
47k6mo agoReviewMountCreate a free account to mount
After finishing, use `ruff format .` and `ruff check .` to format and check the code.
4. When committing, ensure to use conventional commits messages, such as `feat: add new agent
No other project uses it yet
47k30d agoReviewMountCreate a free account to mount