← ClaudeAtlas

deep-reviewlisted

Deep review of branch diffs, working trees, or GitHub PRs at any size. Use when the user asks for CodeRabbit-grade review, an incremental re-review after new pushes, publication of findings to a PR, a cross-LLM peer-review verdict round, or conformance review against spec artifacts. Don't use for applying fixes, reviewing specs or PRDs as documents, or quick single-file feedback.
dougcunha/TokenHound · ★ 3 · Code & Development · score 79
Install: claude install-skill dougcunha/TokenHound
# Deep Review Review at CodeRabbit grade with no file cap and one assertive posture: funnel the diff, discover root/nested project instructions and relevant local skills, shard defects and polish into independent cohorts, fan out reviewers, then merge with complete hunk/rule accounting. Defects require causal evidence and control the verdict; advisories require a concrete improvement and always remain visible. Steps 1–4 drive an idempotent artifact pipeline under `<out>`: every stage gate is a bundled-script exit 0, valid agent outputs are never re-run, and an interrupted round resumes by re-running the same commands. `<skill-dir>` below means the directory containing this SKILL.md; run every bundled command from the repo root. ## Inputs (all optional) | Flag | Meaning | Default | | --- | --- | --- | | `--pr <n>` | Review a GitHub PR (requires authenticated `gh`; head fetched locally) | — | | `--base <ref>` / `--staged` | Local diff scope | merge-base with the origin default branch | | `--worktree` | Review uncommitted + untracked work against the base ref (always a full round) | — | | `--files <p1,p2>` | Restrict review to these paths | full diff | | `--spec <path>` | Spec file or directory; its contract-bearing artifacts become the conformance baseline (spec-parity sweep + verdict gate) | — | | `--subagent <runtime>` | Step 3 reviewer runtime: `native` \| `claude-opus` \| `grok` \| `codex` — non-native runs cross-LLM via `compozy exec` | `native` | | `--max-cohort-file