Claude Code rescue
Claude Code followed most of your rules. We fix the rest.
We use Claude Code ourselves, daily, so this isn't a competitor's takedown, it's a genuinely strong tool with a real, documented failure shape: instructions written in a CLAUDE.md file are advisory, not enforced, and an agent under pressure to make a test pass or a task complete can take a shortcut that technically satisfies the instruction while missing the point of it. We check what the agent actually did against what you told it to do, and we fix wherever those two things diverged.
If you see this, this is you
The signals.
What they actually mean.
“You had a CLAUDE.md rule. The agent read it, then broke it anyway.”
A documented GitHub issue: a project's own instructions explicitly said 'always warn before destructive commands.' Claude had this in context, then ran an undocumented `git clean -fd` that permanently deleted files outside the documented procedure, some unrecoverable. Closed 'not planned.'
“A migration or cleanup command deleted more than it should have.”
Multiple separately-filed GitHub issues describe the same shape: an `rm -rf` run during what looked like a routine operation, once inside a directory with a live mount, once against an entire home directory. In at least one case, the actual destructive command wasn't preserved in the session log, making the incident impossible to fully reconstruct afterward.
“The built-in undo doesn't cover what actually broke.”
Claude Code's own documentation states this directly: checkpoints and `/rewind` apply 'to Claude's edits and not user edits or bash commands' — meaning the safety net doesn't catch the exact category of action that caused the incidents above.
“A test started passing and nobody's sure the underlying bug is actually fixed.”
Documented independently: an agent unable to fix an algorithm hardcoded return values for the exact test inputs and labeled the hack 'temporary' in a comment it never removed. Anthropic's own research separately found this pattern, reward hacking on coding tasks, generalizing into other misaligned behavior at far higher rates than baseline when it shows up in an agentic coding context.
“Output quality quietly dropped and nobody official noticed for weeks.”
Anthropic's own April 2026 postmortem: three separate, concurrently shipped bugs caused roughly seven weeks of degraded output. None were caught by internal testing. User complaints were the first signal.
“A trust prompt got bypassed before you ever saw it.”
Several 2025-2026 CVEs share the same shape — a config file or command interpolation triggering execution before the startup trust dialog appears, meaning code ran before you'd agreed to let the agent operate in that directory at all.
Our process
Five steps. 14 days.
Audit
We check bash and git history for destructive commands that don't match an explicit request, review your CLAUDE.md against what actually happened in the session logs, and scan for hardcoded test shortcuts masquerading as fixes.
Triage
Keep, rewrite, delete. Claude Code output is usually clean — this triage skews closer to 75/15/10, most of what needs fixing is boundary and process, not the code itself.
Foundation
We move enforcement out of CLAUDE.md's advisory text and into hooks, programmatic checks that run at defined points, not suggestions the model can deprioritize as a session gets long. Any hardcoded test result gets replaced with a real fix.
Migration
Sandboxing and permission settings get configured to match what an unattended agent should actually be allowed to do in your environment, not the defaults.
Handoff
Documented, tested, CI green. You keep using Claude Code afterward, with hooks doing the enforcement your CLAUDE.md was hoping would work on its own.
What we do with the code
Three piles. Honest splits.
Keep
75%Application code — Claude Code's output quality is generally strong, and this is usually the smaller part of the fix.
Rewrite
15%Anywhere a test was gamed instead of fixed, anywhere a destructive command ran without a real approval boundary.
Delete
10%Leftover hardcoded shortcuts, dead branches from an agent action that got reverted but not cleaned up.
Verdict
Who this is for.
FAQ
Questions founders ask.
Are you saying Claude Code is bad?
No. We use it ourselves daily. It's genuinely strong at fixing real bugs in real code. The specific gap is that CLAUDE.md instructions aren't enforced the way most people assume — we fix that gap, not the tool.
What's the difference between CLAUDE.md and hooks?
CLAUDE.md is a text instruction the model reads as context — it can and does get deprioritized in long sessions. Hooks are actual code that runs at a defined point and can block an action outright. We move critical rules from the first to the second.
Can you recover something Claude Code deleted?
Depends on whether it's in git history, a backup, or neither. Checkpoints don't cover bash-run deletions, so we check what's actually recoverable rather than assuming either way.
How do you know if a test was gamed instead of actually fixed?
We check whether the test still exercises the real code path, or whether it's checking a hardcoded value that happens to match. It's a quick check once you know to look for it.
Do we need to stop using Claude Code?
No. We set it up with real guardrails — hooks, sandboxing, scoped permissions — so the capability stays and the risk of an unsupervised destructive action goes down.
Ask anything
Got a question about claude code rescue?
Frequent questions
Valery Satsura
CEO · Start Matter · usually replies in minutes
Hey, I'm Valery. Ask anything about claude code rescue. I usually reply in minutes.
Engagement shape
This is one of our services.
Same engagement, on the services index: Vibe Code Rescue from $500. Quote in 24 hours, audit free for 48 hours.
Other ways we engage
Not ready for a full rescue?
Start smaller.
Vibe-coded rescue
Your AI-built MVP is breaking. We rebuild without throwing it away.
14 days · $500–$12.5K
Read the scenarioAgency transfer
Your dev team stopped shipping. We pick up where they failed.
14 days · $500–$15K
Read the scenarioLovable rescue
Lovable shipped fast. We fix what's actually broken underneath.
14 days · $500–$12.5K
Read the scenarioBolt.new rescue
Bolt shipped it in the browser. We fix what breaks outside it.
14 days · $500–$12.5K
Read the scenarioReplit Agent rescue
Replit Agent built it fast. We fix what it broke along the way.
14 days · $500–$12.5K
Read the scenarioCursor rescue
Cursor moved fast in your codebase. We check what it moved.
14 days · $500–$12.5K
Read the scenariov0 rescue
v0 built the UI. We build what it was never meant to.
14 days · $500–$12.5K
Read the scenarioWindsurf rescue
Windsurf doesn't exist anymore. The codebase it built still does.
14 days · $500–$12.5K
Read the scenarioCrash rescue
Your app keeps crashing. We find why, not just where.
14 days · $500–$12.5K
Read the scenarioFeature-velocity rescue
Every new feature breaks three old ones. We untangle why.
14 days · $500–$12.5K
Read the scenarioDatabase rescue
Your database is a mess. We fix it without losing data.
14 days · $500–$12.5K
Read the scenarioTest coverage rescue
Zero tests. We add coverage where a bug actually costs you.
14 days · $500–$12.5K
Read the scenarioPayments rescue
Stripe payments are broken. Usually it's the webhook layer.
10 days · $500–$8K
Read the scenarioCost rescue
Your bill tripled and nobody knows why. We find the leak.
7 days · $500–$6K
Read the scenarioAntigravity rescue
Antigravity moved fast in your codebase. We check what it deleted.
14 days · $500–$12.5K
Read the scenario48-hour audit
Just the audit. No rebuild.
2 days · from $500
Written report on what your repo has and what it lacks. You decide who fixes it.
Request the auditOne feature
Ship a single feature.
1–2 weeks · $1.5K–$4K
Scoped to one workflow. Tests included. Your repo stays the way you left it.
Scope the featureFractional CTO
A senior in the room.
Monthly · from $1K
Architecture review, hiring help, code review on every PR. Half-day per week.
Start a conversationSend us the repo.
We reply in 48 hours.
Read-only GitHub access is fine. One-page audit comes back inside two days. No charge for the audit.