Your coding agents cannot reach production.
Proven with tests, in your CI.

Guardrails for teams on Claude Code and Cursor. Installed in your repos in five evenings. You pay after the test suite passes.

מעקות בטיחות לסוכני קוד: מותקנים ברפו שלכם, מוכחים בבדיקות ב-CI, משלמים רק אחרי שהבדיקות עוברות.

Where do you stand today? Paste your settings.json and CLAUDE.md into the grader. Score out of 10, the specific gaps, nothing uploaded. For a full exposure report with a repo scan (secret files, secret-looking strings, writable pipelines), run gates/exposure_report.py from the kit locally, or send me the two files and get it written within 48 hours. See a sample report. Or take the free kit: agent-guardrails-kit on GitHub, 125 passing assertions.

Why now

On 25 April 2026 a Cursor agent at PocketOS hit a credential mismatch in staging, found an infrastructure token in an unrelated file, and deleted the production database and its volume backups in one API call. Thirty hours down, three months of customer data gone.

Every post-mortem names the same causes: over-privileged tokens in reach of the agent, no gate on destructive actions, backups in the same blast radius. None of them names the model.

Most teams have a line in CLAUDE.md that says "never touch production". That is a sign, not a lock. The agent reads it and usually complies.

What you get

Delivered asynchronously and in writing. One optional call. NDA before any repo access; your clones are deleted from my machine within 30 days.

Proof, not a promise

This is the lab the service is built from. It runs on my machine today:

$ ./tests/run_tests.sh
  ok   guard still blocks without python3 on PATH
  ok   missing policy file fails closed
  ok   malformed policy file fails closed
  ok   interrupted suite leaves config.json intact
  ...
RESULT: 125 passed, 0 failed

$ rm -rf protected/secrets.env      BLOCKED: 'rm' is not on the read-only allowlist
$ cat protected/README.md           allowed

The guard started as a deny-list (block rm, mv, rmdir). It was defeated in minutes. Every one of these wrote into the protected tree unimpeded:

BypassHow
Other verbscp, tee, dd, sed -i, install, rsync into the protected path
Nested interpretersh -c "rm protected/x", perl -e 'unlink ...'
Variable indirectionP=protected; rm $P/x
Subshell(cd protected && rm x)
Acting flagfind protected -delete
Pipelinels protected | xargs rm
Clobber operatorecho x >| protected/x

The rule is now inverted: referencing a protected path is denied unless every verb in the command is on a short read-only allow-list. Unknown fails closed. Your install adds your paths, your secrets locations and your git rules (force-push, history rewrite, direct pushes to main) on top of the same mechanism.

Price

One repo
$1,200 / ₪4,000
first three clients, then $1,500. Audit, install, tests in CI, policy, report, 30 days tuning.
Organization
$2,500 / ₪8,000
up to five repos, org-level managed settings, one policy for all.
Care
$300 to 500 / month
a monthly report of every blocked agent action posted to your Slack, the policy re-proven automatically on every Claude Code release, updates when hook semantics change, onboarding of new engineers, one incident review.

Israeli clients: invoice in ₪, VAT as applicable. Other clients: USD invoice by card, ACH or bank transfer. Guarantee: if the test suite does not pass in your CI, you do not pay.

Who

Daniel Meshulam, Israel. I build production pipelines and agents with Claude Code daily and I run a hooks lab with 125 passing assertions. I am one person: fixed scope, written delivery, no upsell meetings.

Start

Reply with your repo host (GitHub or GitLab), your CI, and which agents your team runs. I answer in writing within 48 hours with a free first review of your current settings.

Email Daniel

meshulam791@gmail.com