try-works/recursive-mode/recursive-review-bundle

Claude Code and agent skill by try-works/recursive-mode

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when recursive-mode work needs a canonical delegated-review or audit handoff. Generates reproducible review bundles for Phase 3.5 code review, test review, or other delegated checks using the repo review-bundle scripts.

Install

npx vskill@latest install try-works/recursive-mode/recursive-review-bundle

SKILL.md

recursive-review-bundle

Use this skill to prepare a canonical review bundle before delegating an audit or review in recursive-mode.

This skill does not replace /.recursive/RECURSIVE.md. It packages the context bundle that delegated reviewers need so the review is durable, reproducible, and acceptable to the workflow.

Canonical Scripts

Use the repo scripts:

  • ./.recursive/scripts/recursive-review-bundle.py
  • ./.recursive/scripts/recursive-review-bundle.ps1

Prefer the Python script when both toolchains are available. Use the PowerShell wrapper when the delegated path is already PowerShell-oriented.

Minimum Inputs

Provide all of:

  • repo root
  • run id
  • phase name
  • reviewer role
  • artifact path being reviewed
  • exact upstream artifact paths
  • relevant audit questions
  • required output shape

Add explicit evidence refs or addenda when they matter. The bundle generator will also auto-discover relevant addenda and skill-memory refs when applicable.

Typical Commands

bash
python ./.recursive/scripts/recursive-review-bundle.py \
--repo-root . \
--run-id "<run-id>" \
--phase "03.5 Code Review" \
--role code-reviewer \
--artifact-path "/.recursive/run/<run-id>/03.5-code-review.md" \
--upstream-artifact "/.recursive/run/<run-id>/00-requirements.md" \
--upstream-artifact "/.recursive/run/<run-id>/02-to-be-plan.md" \
--routing-config-path ".recursive/config/recursive-router.json" \
--routing-discovery-path ".recursive/config/recursive-router-discovered.json" \
--routed-cli "codex" \
--routed-model "gpt-5.4" \
--audit-question "Which R# remain incomplete?" \
--required-output "Findings ordered by severity"
powershell
pwsh -NoProfile -File ./.recursive/scripts/recursive-review-bundle.ps1 `
-RepoRoot . `
-RunId "<run-id>" `
-Phase "03.5 Code Review" `
-Role code-reviewer `
-ArtifactPath "/.recursive/run/<run-id>/03.5-code-review.md" `
-UpstreamArtifact "/.recursive/run/<run-id>/00-requirements.md","/.recursive/run/<run-id>/02-to-be-plan.md" `
-RoutingConfigPath ".recursive/config/recursive-router.json" `
-RoutingDiscoveryPath ".recursive/config/recursive-router-discovered.json" `
-RoutedCli "codex" `
-RoutedModel "gpt-5.4" `
-AuditQuestion "Which R# remain incomplete?" `
-RequiredOutput "Findings ordered by severity"

Acceptance Rules

  • Record Review Bundle Path in the delegated phase artifact.
  • Refresh the bundle after material repairs or scope changes.
  • Require the reviewer to cite the bundle path, upstream artifacts reread, relevant addenda, changed files or code refs reviewed, and a final verdict.
  • Do not treat a bare bundle file as proof of review quality; the written review still has to use the bundle contents.

Routing Awareness

If the prepared bundle will be handed to a routed reviewer, re-read:

  • /.recursive/config/recursive-router.json
  • /.recursive/config/recursive-router-discovered.json

immediately before the delegated call, and include the relevant routing-path citations in the review or action-record metadata.

References

  • /.recursive/RECURSIVE.md
  • /docs/templates/commands/recursive-review-bundle.md
  • ../recursive-subagent/SKILL.md

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
119
Repository forks
9
7-day trend score
24

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/try-works/recursive-mode/recursive-review-bundle/badge)](https://verified-skill.com/skills/try-works/recursive-mode/recursive-review-bundle)

Something wrong with this skill or its page? Tell us.