scan-codebase
Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.
git clone --depth 1 https://github.com/Agenta-AI/agenta /tmp/scan-codebase && cp -r /tmp/scan-codebase/.agents/skills/scan-codebase ~/.claude/skills/scan-codebaseSKILL.md
# Scan Codebase Read these shared references when needed: - `../shared/references/findings.schema.md` - `../shared/references/findings.lifecycle.md` ## Role Run a fresh review pass from code and docs into findings. - This skill is verification-oriented. - It may surface missing tests or coverage gaps as findings. - It does not rely on existing findings as the starting point. - It does not replace `test-codebase`; if runtime validation is needed, hand off there. ## Depth Accept a `depth` parameter from the prompt: - `shallow` - `deep` Default: - `depth=deep` ## Path Input Accept an optional `path` from the prompt. - If `path` is provided, use it as the local design or findings folder. - If `path` is omitted, infer it from the branch, subsystem, or matching docs and state the inferred value before starting. Default: - `path=infer` ## Workflow 1. Establish scan scope. Confirm the effective variables first: - `path` - `depth` - branch, base, subsystem, and any requested focus areas 2. Start from fresh context. Read current code, docs, tests-as-code, routes, schemas, migrations, and adjacent design material before looking at existing findings. 3. Produce findings from review. Surface correctness, consistency, completeness, soundness, functionality, security, performance, compatibility, migration, and missing-test findings when supported by evidence. 4. Update the active findings record. Use `path/findings.md`. 5. Hand off when execution is needed. Use `triage-findings` for discussion and planning, `test-codebase` for validation, and `resolve-findings` for implementation. ## Rules - Bias toward deep inspection, not prior-thread anchoring. - Do not silently preload old findings into the initial reasoning path. - Do not present test execution as completed if you only inferred missing coverage from code.
Helps add announcement cards to the sidebar banner system. Use when adding changelog entries, feature announcements, updates, or promotional banners to the Agenta sidebar. Handles both simple changelog entries and complex custom banners.
Playbook for adding a new coding-agent harness to Agenta (Codex, Hermes, Gemini, OpenCode, ...). Use when starting, planning, or reviewing a new-harness project. Covers the readiness audit of prior art, the spike-first milestone plan, the full integration-surface checklist, the per-harness variance axes to probe, and the process/communication contract with Mahmoud. Living document: every harness project appends its lessons to resources/LESSONS.md.
>-
Where to put frontend code (package vs app layer) and how to use the @agenta/* packages. Use when authoring or moving code in web/packages, choosing between @agenta/ui, @agenta/entities, @agenta/entity-ui, @agenta/shared, @agenta/playground, using molecules, loadable/runnable bridges, the EntityPicker, or writing package unit tests.
Use this skill to create and publish changelog announcements for new features, improvements, or bug fixes. This skill handles the complete workflow - creating detailed changelog documentation pages, adding sidebar announcement cards, and ensuring everything follows project standards. Use when the user mentions adding changelog entries, documenting new features, creating release notes, or announcing product updates.
Hard-won GitButler mechanics for multi-lane work in this repo — committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace. Use when working with stacked branches, when `but rub`/`but absorb`/`but commit --only` mis-routes a change, when a stack collapses or a commit lands on the wrong lane, or when a hunk gets dropped. Not needed for ordinary single-lane work.
Drive a researched and planned feature to a landed, tested change. Use after plan-feature has produced a docs/design/<project>/ workspace and the user says "implement it", "build the plan", "run the plan", or "let's ship this". Orchestrates refresh-plan, implement, review, a debug-local-deployment loop, and a test loop across the daytona / local-pi / claude x SDK / UI matrix, then documentation and a GitButler stacked branch. The orchestrator stays in the loop and spins narrow subagents for each phase.
Feature-folder layout, states/ convention, and data-flow rules for the Agenta mobile app (web/mobile). Use when creating or moving files under web/mobile, deciding where a component lives, adding a new feature or screen, or wiring data into mobile components.