content is primarily markdown documentation for educational purposes around prompt engineering and LLM security research.
## Repository Structure
- **SystemPrompts/** - System prompts from various LLM providers (OpenAI, Anthropic, Google, Meta
5.5k3mo agoReviewMountCreate a free account to mount
Changelog 1.1.0](https://keepachangelog.com/en/1.1.0/).** Bullets grouped under Added / Fixed / Changed / Deprecated / Removed / Security; one bullet per change; PR link for the deep dive; inline **BREAKING** prefix for breaking changes
5.5k33d agoReviewMountCreate a free account to mount
writes to live app configuration files, proxy routing or failover, concurrency, credentials or other security-sensitive paths, or import, export and sync of user data. Every reviewer inspects that round
5.5k3d agoReviewMountCreate a free account to mount
ancestor, but KasmVNC deliberately breaks RFB to support
modern transport, encodings, and security. **Do not "fix" code toward RFB-spec
compliance** — divergence is intended. (A detailed list of the deviations
5.4k4y agoReviewMountCreate a free account to mount
never reuse, never user-chosen, never "remember." The entire "offline crack is worthless" security argument depends on this (see the crypto doc §7). The discovery HMAC key is derived from
5.4k23d agoReviewMountCreate a free account to mount
effect refactors) is out of scope
for agents. Maintenance is interrupt-only: red CI, security, human-reported
bugs.
- Two skills drive it: `next-idea` (ideation — files locked `idea` issues,
never
5.4k4mo agoReviewMountCreate a free account to mount
service configured with
just one of the two. Entries now carry a separate `secure` endpoint.
6. **No crash-safety whatsoever.** `SIGKILL`, a force-quit or a `npm run dev`
reload
4.9k4mo agoReviewMountCreate a free account to mount
enter default
builds, CI, publication, or behavioral-parity requirements without a
separately approved design.
## Security Model
Trust model:
- **Client**: trusted, except for code/payloads it submits for execution.
- **Sidecar/runtime**: trusted enforcement
4.9k46d agoReviewMountCreate a free account to mount
architectural invariant. Any path where guest code reaches the real host is a critical security violation.
**NEVER use `Command::new("node")` for guest code execution.** Guest JavaScript runs inside
4.9k46d agoReviewMountCreate a free account to mount
lint
```
- ALWAYS run tests after making code changes
- ALWAYS verify build succeeds before committing
## Security Rules
- NEVER hardcode API keys, secrets, or credentials in source files
- NEVER commit .env files
Steady2 mentions in 2 weeks
1 project uses a version of this
4.7k10d agoReviewMountCreate a free account to mount
opus"` only for architecture, new dialects, cross-cutting refactors, unknown-root-cause debugging or security-sensitive changes. Escalate only with a stated reason.
**Reference:** `.cursor/rules/planning-and-delegation.mdc`
## When to Apply Rules
No other project uses it yet
4.6k38d 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.