nour-command
Use for any non-trivial Nour task that needs context recovery, end-to-end execution, MAX EFFORT, backlog reconciliation, deep research, audit-and-fix work, or proof-backed completion. Also use when No
SKILL.md.claude/skills/nour-command/SKILL.md
GitHubNOUR COMMAND
This skill is a router, not a second policy.
- Read
../../../AGENTS.md; it is the engineering/safety authority. - Read
../../../NOUR-COMMAND.md; apply its execution framework. - If the task is non-trivial, read only the relevant entries in
../../../docs/agent-os/NOUR-COMMAND-MODES.md. - Load the nearest app
AGENTS.mdbefore editing app code. - Invoke any narrower repo skill whose trigger applies; this router does not replace domain skills.
- Define the task-specific completion contract before consequential execution.
- Recover context before asking Nour to repeat prior work.
- Verify current remote/production truth before trusting a prior session, plan, or local checkout.
- Prefer finish/wire/repair/consolidate/adopt/delete before adding another implementation.
- Execute in dependency order and run authorized work to empty.
- Try to falsify apparent success before declaring completion.
- Simplify after a successful change and turn material failures into regression protection.
- Report demonstrated outcomes, exact proof, real remaining work, and exact blockers.
When AGENTS.md or an app-specific instruction conflicts with this skill, the canonical policy wins.
For Claude, NOUR-COMMAND.md is imported by root CLAUDE.md, so the main framework is already in context.
This skill exists to make the mode-router invocation explicit and to force loading only the relevant deep-mode details.