Loop Operator Kit ל-Claude Code

LOOP BUDGET

Goal:
[תוצאה אחת שאפשר לבדוק]

Limits:
- max_runtime_minutes: [מספר]
- max_attempts: [מספר]
- max_cost: [סכום או טוקנים]

After every attempt, record:
- what changed
- which check passed
- which check failed

Stop and escalate when any limit is reached.
Return the last evidence and the smallest decision I need to make.

RUNTIME DECISION

Must continue while laptop is closed?
-> Cloud routine

Needs the current conversation context?
-> /loop inside the open session

Needs local-only files or tools?
-> Desktop scheduled task

Needs more than one of these?
-> Move the missing context or files to a shared source,
   or split the workflow at an explicit handoff.

MODEL ROUTING CARD

Task: [השלב בלופ]
Failure impact: low / medium / high
Verification cost: low / medium / high
Baseline model: [המודל האמין]
Cheaper candidate: [מודל לבדיקה]

Run both on the same sample.
Keep the cheaper model only if:
1. the required checks still pass,
2. retries do not increase,
3. human repair time does not increase.

SAFETY LAYERS

Instruction layer:
- Write the expected behavior in CLAUDE.md.

Enforcement layer:
- Deny dangerous tool patterns.
- Add a PreToolUse check before production commands.

Environment layer:
- Use an isolated worktree or sandbox.
- Keep production credentials unavailable.

Human gate:
- Require explicit approval for deploy, delete, payment,
  customer messages, and irreversible changes.

COMPLETION CONTRACT

Deliverable:
[התוצאה הסופית]

Required proof:
- [test or command]
- [real screen, URL, log, or provider state]

Handoff:
- owner: [מי מקבל]
- package: [מה נמסר]
- approval needed: [כן או לא, ועל מה]

Do not report complete while any required proof is missing.
If waiting, report exactly what is waiting and notify the owner once.

DAILY SENTRY LOOP

1. Pull new production errors since the previous run.
2. Group duplicate fingerprints.
3. Reproduce the highest-impact new error.
4. Apply the fixed debugging skill.
5. Implement inside an isolated branch or worktree.
6. Run the required tests and save the evidence.
7. Open a PR with root cause, risk, and proof.
8. Stop for human approval before merge or deploy.

Record each fingerprint as fixed, rejected, duplicate, or escalated.

FIT CHECK

Use a loop when:
- the trigger is repeatable,
- success is measurable,
- the tools are stable,
- the stop condition is explicit.

Use one full-context agent when:
- later decisions depend on early details,
- summaries would remove important evidence.

Use parallel agents when:
- tasks are independent,
- each output has its own verification.

Keep a human gate when:
- the decision affects money, customers, production, or reputation.