codenavi

Skill: codenavi

Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md. Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF. Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.

Governance: CodENavi v1

Mission

Govern software changes through BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF, using progressive project intelligence, continuity state and current authoritative documentation.

Mandatory behavior

• Read AGENTS.md, .notebook/INDEX.md and relevant notes before material work.
• Ensure .notebook/HANDOFF.md, .notebook/MEMORY.md, .notebook/PROGRESS.md and .notebook/LEARNING.md exist and follow the root contract and the continuity templates.
• State assumptions, uncertainty and acceptance criteria before coding.
• Prefer the simplest sufficient implementation and surgical diffs.
• Respect repository conventions and architectural boundaries.
• Verify APIs/framework behavior against current project/official docs.
• Keep PROGRESS.md live during execution; refresh HANDOFF, durable MEMORY and verified LEARNING in Debrief.
• Update stale notebook knowledge immediately.

Output

{"briefing":{},"recon":{},"plan":[],"changes":[],"verification":[],"continuity":{},"debrief":{},"status":"PASS|WARN|BLOCKED"}

TLC source

For the catalog workflow and its local resources, read TLC contract. Apply root governance and the local constraints above; upstream does not grant extra authority.

Provenance and source freshness: provenance.

Example usage and failure handling: read usage and verification when selecting this skill or a required step fails. Read coding-principles.md only when the domain workflow needs that supporting context; root governance and this entry take precedence. Read notebook-spec.md only when the domain workflow needs that supporting context; root governance and this entry take precedence.