ingest

Cut a release in any repo — derive the next semver from history, promote the changelog, bump every version manifest and lockfile, commit, tag, and push.

Fix every finding /review-issues posted on the pipeline's pull requests: verify the claim first, commit on-layer findings onto the reviewed branch, and file…

Work through GitHub issues labelled priority:high, priority:medium, or priority:low, highest priority first, and land the fixes as file-disjoint stacked PR…

Merge the pull requests the pipeline reviewed and fixed — a gh-stack chain bottom-up with gh stack merge, regular PRs with gh pr merge, or plain git when…

Review the pull requests the pipeline opened (the gh-stack chain from /fix-issues) in a fresh context with an adversarial subagent, and post each finding as a…

Write a structured session debrief into Obsidian and print a ready-to-paste ticket comment (and PR summary when relevant).

Run the whole problem pipeline in one command.

Scan a codebase module-by-module with parallel subagents to find bugs, correctness and security defects, over-engineering, and lean refactoring opportunities…

File report, review, or scan findings as evidence-backed GitHub issues, one per root cause, labelled priority:high/medium/low.

poteto's engineering stack — rigorous, unslopped agent workflows you can parallelize with confidence.

Search the AI Wiki knowledge base by keyword and return all relevant pages and sources, ranked, with wikilinks and one-line descriptions.

Deep codebase cleanup and code quality improvement using 8 specialized subagents.