Skip to content

Fieldnote-Echo/claude-secure-config

Repository files navigation

claude-secure-config

Security rules, cognitive scaffolding, and hook enforcement for Claude Code projects.

Quick start

git clone https://github.com/Fieldnote-Echo/claude-secure-config.git
bash claude-secure-config/setup.sh /path/to/your-repo

Add .claude/rules/org/ to your .gitignore. Updates arrive automatically via git pull.

The problem

AI-generated code produces 1.7x more issues per PR than human code. 87% of AI-generated PRs contain security vulnerabilities. Developers who delegate to AI score 17% lower on comprehension — while those who use AI for conceptual inquiry score highest of all.

The problem isn't AI. It's AI without structure.

Three layers

Layer 1: Hooks      → "You can't do this"      (deterministic enforcement)
Layer 2: Rules      → "Here's how to do this"   (security, hygiene, conventions)
Layer 3: Scaffold   → "Why are we doing this?"  (cognitive partnership)

Layer 1: Enforcement

Hooks are deterministic — they can't be ignored or summarized away.

File What it does
hooks.md Blocks rm -rf, git push --force, --no-verify, .env access. Template settings.json you copy into your project.

Layer 2: Rules

Text instructions the model follows during code generation. Structured as pre-flight checks, non-derivable specifics, and eval anchors.

File What it catches
security.md Trust boundary violations, injection, XSS, unsafe deserialization, secret leaks, supply chain risks, MCP/tool trust
code-hygiene.md Weak types, swallowed errors, fire-and-forget async, code duplication, unverified completion claims
git-conventions.md Force-pushes, skipped hooks, git add ., scope creep, AI mis-attribution

Layer 3: Partnership

Shapes how the model works with you, not just what it produces.

File What it changes
cognitive-scaffold.md Reduces sycophancy, surfaces trade-offs, flags unfamiliar patterns, monitors for dependency formation
deliberation.md Pauses before irreversible actions, builds trust progressively, pushes back when something seems off
task-protocol.md Preflight questions before non-trivial tasks

~255 lines, ~2,922 tokens total. Compliance degrades as instruction volume grows — keep loaded rules concise and verify behavior after changes.

Installation options

The quick start above uses symlinks (recommended). Other options:

Method Command Updates
Copy setup.sh /path/to/repo --copy Re-run to update
Manual Copy individual files to .claude/rules/ Manual
@import @/path/to/rules/security.md in CLAUDE.md Automatic (path must resolve on every dev machine)

Run setup.sh --help for all flags. See the setup.sh reference for provenance tracking and advanced configuration.

Hooks

Text rules can be ignored. Hooks can't. Copy the template from hooks.md into .claude/settings.json.

For isolation beyond hooks: Anthropic's built-in sandbox or Trail of Bits' devcontainer.

Customization

.claude/CLAUDE.md          → Your critical project rules (top of file = highest attention)
.claude/rules/*.md         → Your project-specific rules
.claude/rules/org/*.md     → Shared rules from this repo
internal/*.md              → Private rules (gitignored, install with --internal)

See the wiki for customization patterns, internal rules, and compaction survival.

Limitations

  • Not a replacement for SAST/DAST — these are authoring-time guardrails
  • Not runtime security — implement CSP, rate limiting, and auth middleware in your code
  • Text rules can be compacted away in long sessions — hooks are immune
  • --dangerously-skip-permissions disables all hooks and deny rules
  • AI training can override text instructions — hooks are stronger than rules

Sources

Built on OWASP Top 10:2025, OWASP Agentic Top 10, CWE Top 25, OpenSSF AI Code Assistant Guide, and research on cognitive scaffolding, deliberative alignment, and human-AI feedback loops.

Contributing

PRs welcome. Keep rules generic, concise, and backed by data where possible. See the contributing guide for rule design principles and testing requirements.

License

MIT

About

Security rules, cognitive scaffolding, and hook enforcement for Claude Code — a 3-layer framework for human-AI partnership (hooks → rules → scaffold)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors