repo-native-alignment

Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.

Resolve multi-dependency fan-in by merging dependency PRs into a common base and updating issue dependencies

Review and merge open PRs for GitHub issues as a cohesive batch

Claim a GitHub issue, create its branch and draft PR before implementation, execute the work in isolation, and hand the completed draft to RNA's full ship gate.

Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.

Agent-led PR/working-tree review triage. Start from the diff, add RNA graph/business context only where it changes review decisions, and state when raw git diff is enough.

Install and configure the Repo-Native Alignment (RNA) MCP server. Downloads the binary, configures the MCP server, pre-warms the code index, and updates AGENTS.md with tool guidance.

Clarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to ground the session in strategic intent.

Devil's advocate. Seek contrary evidence before locking in. Use when about to make a significant decision, when confidence is high but stakes are higher, or when the team is converging too quickly.

Human-led curation of accumulated metis and guardrails. Surface patterns across sessions, propose what to promote, compact, or dismiss. Use after multiple sessions, before a new phase, or when search results feel noisy.

Create Jira subtasks from task descriptions or session context. Investigates when needed, skips when context exists.

Diagnose and fix CI failures on a PR, push fixes

Resolve merge conflicts on a PR by merging base into head

Address PR comments for GitHub issue PRs, resolve feedback, push fixes

Create GitHub issues from task descriptions or session context. Investigates when needed, skips when context exists.

Review a PR against its linked issue requirements, post structured feedback

Map what we're optimizing and what constraints we treat as real. Use before jumping to solutions, when hitting repeated blockers, or when patches keep accumulating.

Define the framing of a problem. Change the statement, change the solution space. Use when starting work, when solutions feel wrong, or when you suspect an X-Y problem.

Extract learning before restarting. Code is a draft; learning is the asset. Use when work is drifting, approach has reversed 3+ times, or scope is expanding while "done" keeps fuzzing.

Run RNA's mandatory project-specific quality gate from completed implementation through review, verification, CI, and merge. Use when a draft PR is ready to be delivered.

Explore candidate solutions before committing. Use when you have a problem statement and need to evaluate approaches - band-aid, optimize, reframe, or redesign.

Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.

Detect potentially dead code using RNA graph data. Finds public functions with zero non-test callers. No code changes needed — queries existing graph edges.

Backfill ADR frontmatter with direct executable validation refs, compile/check ADR validation manifests, and report missing real checks without inventing them.

Record a business artifact (.oh/ metis, signal, guardrail, or outcome update). Use when capturing learnings, measurements, constraints, or updating outcome status.

Generate an architecture diagram from RNA data. Queries frameworks, endpoints, entry points, and external service calls, then renders in the user's preferred format (d2, mermaid, plantuml, etc.).