Rippletide for Claude Code

You wrote the rules. Your agent ignored them.

Claude Code proposes changes.

Rippletide decides if they are allowed.

CLAUDE.md was supposed to be the contract between you and your agent. In practice, instructions get ignored, overwritten after compaction, and violated on security-critical rules. Rippletide enforces what CLAUDE.md can only suggest.

~/my-project

$npx rippletide-code

Scanning CLAUDE.md + codebase...

Found 154 rules in your CLAUDE.md. 14 were violated in last 3 sessions.

Top violations:

✗ "DO NOT modify .env files" violated 4x
✗ "Use /lib/api for all API calls" violated 3x
✗ "Tests use data-testid selectors" violated 3x

⚠ 12 implicit conventions detected, not in CLAUDE.md

Context Graph built. Rules are now enforced.

Not suggestions. Constraints.

npx rippletide-code

Works with

  • Claude Code
  • Cursor
  • Windsurf
  • Cline

THE EVIDENCE

This is what developers actually say.

Real reports. Real frustration. All from public GitHub issues on the Claude Code repo.

“Every rule in CLAUDE.md is advisory to the model. There is no enforcement mechanism. Claude can be told to follow rules, and it mostly does, but there is nothing that prevents it from skipping steps during response generation.”
GitHub #32193 · Mar 2026

“The problem is not that Claude cannot read or understand the rules. When asked, Claude can recite them accurately. The problem is that Claude does not check the rules before acting. It acts first, then when the user points out the violation, it acknowledges and apologizes — but the damage is already done.”
GitHub #30421 · Mar 2026

“The agent admitted it read the CLAUDE.md rules and was aware of them, but its default behavior pattern overrode the explicit rules.”
GitHub #29236 · Feb 2026

“Claude.MD and Agents are useless. Agents definitions need to follow the instructions, right now they don't.”
GitHub #7777 · Sep 2025

“Claude Code consistently ignores explicit instructions in CLAUDE.md file and makes unauthorized, destructive changes to production code.”
GitHub #5516 · Aug 2025

“After using /compact, Claude Code stops respecting the instructions in CLAUDE.md and begins to behave unpredictably.”
GitHub #4017 · Jul 2025

WHY THIS HAPPENS

CLAUDE.md is a suggestion. Not a contract.

CLAUDE.md alone makes enforcement impossible. Rippletide brings this infrastructure.

The problem is not that the model doesn't know the rules.

The problem is that knowing a rule is not the same as enforcing it.

Claude Code may understand your architecture and still violate it when executing a change. Rippletide turns those rules into executable decisions.

THE AGENT LOOP

Where Rippletide sits in the agent loop

Two intervention points. Plan mode and runtime. Nothing else changes.

Claude Code

↓

Rippletide provides decision context

↓

PLAN MODE

↓

Rippletide validates plan or ask for modifications

↓

Agent proposes next action

↓

[Hook] Rippletide validates the decision

↓

Allowed / Blocked

↓

TOOL CALL

↓

Repository mutation

HOW IT WORKS

One command. Rules that stick.

Rippletide uses your codebase and session history to build a Context Graph, and enforces your conventions through hooks at every agent action.

  1. Scan

    • Reads your codebase + existing CLAUDE.md. Extracts implicit conventions: naming, architecture, patterns, test strategies, security boundaries.

  2. Build the Context Graph

    • The graph is not documentation. It is the structure Rippletide uses to decide whether a change is allowed. Conventions become structured nodes with relationships, not a flat file.

  3. Enforce via hooks

    • Rippletide does not run inside the model. It intercepts the agent's tool calls and decides whether the action may execute. Before your agent writes code, edits a file, or runs a command, it checks the graph.

  4. Learn from corrections

    • Every time you amend a CLAUDE plan or modify CLAUDE's output in a session, the graph updates. Conventions evolve with your codebase and previous corrections.

What you get

  • Rule enforcement: Your CLAUDE.md rules become enforceable constraints. The agent doesn't "try to follow" them. It can't violate them.
  • Convention detection: Scans your codebase and session history and finds the implicit rules you never wrote down. Naming, structure, patterns. Auto-detected, auto-enforced.
  • Context always up to date: The graph stays up to date. After every plan correction or Claude feedback, it reflects what actually happened.
  • Compaction-proof: The Context Graph lives outside the context window. /compact, new session, crash: your rules survive. Always.
  • Hook native: Built on Claude Code hooks, not MCP. No tokens wasted injecting rules into every prompt. Enforcement happens at the tool call level.
  • Security boundaries: "DO NOT TOUCH CREDENTIALS" actually means something. Security rules get the highest enforcement priority. No exceptions.

YOUR DATA

Rippletide never reads your codebase directly. Your Claude Code does the work, we only collect the results.

STAYS ON YOUR MACHINE

  • Your source code, never seen by Rippletide
  • File contents, never seen by Rippletide
  • Project session history, seen by Rippletide to infer rules but never stored
  • Your CLAUDE.md rules, seen by Rippletide but never stored

STORED IN THE CONTEXT GRAPH

  • Rules inferred
  • Extracted conventions and naming patterns
  • Architecture boundaries
  • Reviewer preferences
  • Nothing else

Rippletide asks your Claude Code to look for specific conventions. We never access your source code directly. Only rules and patterns are sent to the Context Graph.

DECISIONS

Decisions Rippletide makes for Claude Code

Rippletide decides whether Claude Code may:

  • ✗ Edit sensitive files
  • ✗ Break architecture conventions
  • ✗ Bypass test requirements
  • ✗ Introduce forbidden patterns
  • ✗ Run risky commands

THE NUMBERS

The model isn't the problem. Control is.

Public data from the Claude Code repo. The pattern is clear.

  • 50% of Claude Code CLAUDE.md issues are about rules being ignored
  • 18+ public reports of CLAUDE.md non-compliance on GitHub
  • 0 enforcement mechanisms in CLAUDE.md today
  • <60s to build a Context Graph and start enforcing

Sources: anthropics/claude-code GitHub issues, corpus of 21 public reports, March 2025 - March 2026.

Claude Code is the first surface.

Rippletide is the decision infrastructure for any agent that executes actions.