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
8.1k4d agoReviewMountCreate a free account to mount
generate` are not read-only: they can rewrite generated code, manifests, module files, formatted Go files, or test artifacts. Review the resulting diff and keep only task-related changes
code in this repo is named, typed, structured, formatted, tested, and reviewed. Pure Python coding standard; framework-agnostic.
- **`documents/ai/guides/serena.md`** — Always-on. When and how to use Serena MCP for symbol
7.9k14mo agoReviewMountCreate a free account to mount
code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
- `.claude/skills/best-practices/SKILL.md`
## Core Web Vitals optimization
Optimize Core Web Vitals
7.8k7mo agoReviewMountCreate a free account to mount
request without manual review by a human. Do not file AI generated issues under any circumstances.
Using AI generated content in issue/PR discussions might lead to code of conduct violations
No other project uses it yet
7.8k2mo agoReviewMountCreate a free account to mount
translations:
- Translate the prose; leave identifiers, paths, `make` targets, URLs, env var names, code blocks
and route strings verbatim in English.
- Headings are translated, so the `Content` index anchors
7.7k43d agoReviewMountCreate a free account to mount
skill creation
- Converts raw PM content into skills via 8-step workflow
- Supports Claude Code, Manual mode (`--agent manual`), and custom adapters
- Includes analysis, planning, generation, validation, and documentation steps
Steady6 mentions in 2 weeks
No other project uses it yet
7.7k3mo agoReviewMountCreate a free account to mount
after refreshing against latest `origin/main`.
Docs-only changes: review rendered Markdown and `git diff --check`; no runtime tests required.
---
## Claude Code session checklist
Before editing:
1. Confirm
7.6k54d agoReviewMountCreate a free account to mount
with code in this repository.
## Project Overview
SEO Machine is an open-source Claude Code workspace for creating SEO-optimized blog content. It combines custom commands, specialized agents, and Python
7.5k8mo agoReviewMountCreate a free account to mount
Pointers Are `fl::shared_ptr`"
- **JavaScript**: Run `bash lint --js` after modifying JS files
### CodeReview Rule
**ALL AGENTS: Run `/code-review` after making code changes.**
Before opening a feature
7.5k40d agoReviewMountCreate a free account to mount
provided:
```bash
git checkout -b githubusername-gh-1234_add_new_feature
```
### Pull Requests
- New code requires unit tests (runits for R, pyunits for Python, JUnits for Java)
- PR title should
7.5k4y agoReviewMountCreate a free account to mount
halves:
- **Interactive skills** (`.claude/skills/`) — read and write files in the
repo (no target-code execution, except `/dnr-hunt` / `/dnr-respond`, which
run the bundled demo app locally — see `docs/security.md`), run in this
No other project uses it yet
7.5k4mo agoReviewMountCreate a free account to mount
every matching sub-design.
**Rules for agents reading this repo:**
1. Before writing or reviewingcode in a component, read that component's
`DESIGN.md` (or, for Felix, the sub-designs
7.4k2mo agoReviewMountCreate a free account to mount
build, run tests, debug, and use Felix-specific tooling.
For **architecture, invariants, and review criteria**, see [`felix/DESIGN.md`](./DESIGN.md) — the design index — and the per-topic sub-designs under [`felix/design/`](./design
7.4k2mo agoReviewMountCreate a free account to mount
cross-cutting mechanism, not "just a UI feature."** Treat it like one before writing code: trace every existing consumer of the data it needs (e.g. everything that already reads `app_state.json
7.3k21d agoReviewMountCreate a free account to mount
guides/
└── v12_examples/ # New v12 feature examples
```
Look in `examples/` first before writing new code — there is almost certainly an existing example close to what you need.
---
## Core Primitive: Agent
7.3k2y agoReviewMountCreate a free account to mount
history → the commit message or PR body
- a personal preference (whether you use worktrees, review habits, voice) → your `CLAUDE.local.md` or
`~/.claude/CLAUDE.md`, never a committed file
`no-claude-md-bloat` caps
7.3k3d agoReviewMountCreate a free account to mount
code changes, verify size impact with agentrc's `code-size` (the build contract's Code size section).
## PRs and Follow-ups
- Before opening or updating a PR, follow Build
7.3k2d 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.