Agent skill

Recursive Review Bundle

by try-works in try-works/recursive-mode

A skill your agent uses when recursive-mode work needs a canonical delegated-review or audit handoff.

Apache-2.0Auto-check passedDevelopment

Install Recursive Review Bundle

skills CLI
$ npx skills add try-works/recursive-mode --skill recursive-review-bundle -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install try-works/recursive-mode recursive-review-bundle --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/try-works/recursive-mode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recursive-review-bundle .claude/skills/recursive-review-bundle && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recursive-review-bundle
GitHub stars
136
Token cost
~873 tokens
SKILL.md length
225 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when recursive-mode work needs a canonical delegated-review or audit handoff.

  • Recursive-mode work needs a canonical delegated-review
  • SKILL.md covers Canonical Scripts, Minimum Inputs, Typical Commands and Acceptance Rules, plus 2 more sections
  • Calls python and pwsh

What it does

Recursive Review Bundle is an agent skill from try-works/recursive-mode. 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.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development. The repository describes itself as: Recursive workflow for agentic engineering. Like Factory Missions but properly recursive, free and open source. The licence is Apache-2.0.

When your agent uses it

  • Recursive-mode work needs a canonical delegated-review

Example prompts

  • “/recursive-review-bundle”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit ff75bc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • pwsh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recursive Review Bundle loads about 873 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 225 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~873

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from try-works/recursive-mode at commit ff75bc7, republished under its Apache-2.0 licence (© try-works). 225 words, ~873 tokens.

Download SKILL.mdSave it as .claude/skills/recursive-review-bundle/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
recursive-review-bundle
description
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.

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

© try-works, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/recursive-review-bundle of try-works/recursive-mode.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit ff75bc7

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in try-works/recursive-mode, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Recursive Review Bundle next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recursive Review Bundle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recursive Review Bundle this skilltry-works/recursive-mode136—~873Automated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from try-works/recursive-mode

All 9 skills in this repo
  • Recursive Mode

    try-works/recursive-mode

    Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance.

    136 GitHub stars~3.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Recursive Debugging

    try-works/recursive-mode

    A skill your agent uses when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior.

    136 GitHub stars~3.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Recursive Subagent

    try-works/recursive-mode

    A skill your agent uses when recursive-mode work may benefit from delegated audit, review, or bounded implementation support.

    136 GitHub stars~3k tokensUpdated 2 mo ago
    Auto-check passed
  • Recursive TDD

    try-works/recursive-mode

    A skill your agent uses when implementing any code in recursive-mode Phase 3.

    136 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Recursive Worktree

    try-works/recursive-mode

    A skill your agent uses when starting any recursive-mode requirement to set up an isolated git worktree.

    136 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Recursive Spec

    try-works/recursive-mode

    Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs.

    136 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Recursive Review Bundle

What does Recursive Review Bundle do?

A skill your agent uses when recursive-mode work needs a canonical delegated-review or audit handoff. Recursive Review Bundle is an agent skill from try-works/recursive-mode. Use when recursive-mode work needs a canonical delegated-review or audit handoff.

When should I use Recursive Review Bundle?

Recursive Review Bundle fits situations like: recursive-mode work needs a canonical delegated-review.

How do I install Recursive Review Bundle in Claude Code?

Run `npx skills add try-works/recursive-mode --skill recursive-review-bundle -a claude-code`. Or copy the skill folder (skills/recursive-review-bundle in try-works/recursive-mode) into .claude/skills/recursive-review-bundle in your project. Claude Code loads it when a task matches its description.

How do I install Recursive Review Bundle in Codex?

Run `npx skills add try-works/recursive-mode --skill recursive-review-bundle -a codex`. Or copy the skill folder (skills/recursive-review-bundle in try-works/recursive-mode) into .agents/skills/recursive-review-bundle in your project. Codex loads it when a task matches its description.

Can I use Recursive Review Bundle in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add try-works/recursive-mode --skill recursive-review-bundle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recursive-review-bundle, .gemini/skills/recursive-review-bundle, .github/skills/recursive-review-bundle and .opencode/skills/recursive-review-bundle in your project.

What does Recursive Review Bundle need to run?

Going by SKILL.md and its folder, Recursive Review Bundle needs the command-line tools its instructions call (python and pwsh). Our summary lists: Python 3.

Does Recursive Review Bundle access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Recursive Review Bundle safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recursive Review Bundle use?

Recursive Review Bundle is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recursive Review Bundle use?

About 873 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Recursive Review Bundle?

Skills that share tags, products or a category with Recursive Review Bundle: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recursive Review Bundle?

try-works (a GitHub user) maintains it in try-works/recursive-mode, which has 136 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on July 24, 2026.

Source: try-works/recursive-mode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.