القائمة
Use after PR-sized work completes (or on /mek-drift) to compare auto scores against .mek/drift-baseline.json and surface divergences > 0.15.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when the agent is about to perform a risky operation (destructive shell, deploy, schema migration, money write, force-push). Reminds to record HITL approval and points at compliance/ templates.
STUB. Future v0.2.0 feature — a mini-SQLite ledger so the agent can record/query journal entries for any context (token spend, invoicing, etc.). Not active in v0.1.0.
Use when the agent encounters money-shaped identifiers (amount, price, balance, total, cost), performs arithmetic across monetary fields, or writes/reads money to a database. Enforces Decimal-only math.
Use when starting any conversation in a project where MEK is installed - announces the three guardrails (compliance, drift, ledger) and how to invoke them.
| name | drift |
| description | Use after PR-sized work completes (or on /mek-drift) to compare auto scores against .mek/drift-baseline.json and surface divergences > 0.15. |
/mek-drift..mek/drift-baseline.json (created by /mek-drift init).|auto - manual| > divergence_threshold (default 0.15) AND confidence >= min_confidence (default 0.5), ORauto < floor (ratchet violation)./mek-drift accept — agree with auto, update manual to match./mek-drift ack — disagree with auto, dismiss this flag (record in baseline metadata).mek.toml > [drift]:
[drift]
baseline_file = ".mek/drift-baseline.json"
preset = "python"
divergence_threshold = 0.15
min_confidence = 0.5
auto_run_on_stop = true