Agent skill

Besimple Broccoli Blind

by besimple-oss in besimple-oss/broccoli

Non-interactive wrapper: plan-sketch - auto-pick recommended options - plan-write - plan-critique-loop - implement-from-plan - claude-simplify-wrapper - dedup - code-review-loop.

MITAuto-check passedDevelopment

Install Besimple Broccoli Blind

skills CLI
$ npx skills add besimple-oss/broccoli --skill besimple-broccoli-blind -a claude-code

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

GitHub CLI
$ gh skill install besimple-oss/broccoli besimple-broccoli-blind --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/besimple-oss/broccoli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/prompt-templates/skills/besimple-broccoli-blind .claude/skills/besimple-broccoli-blind && 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
besimple-broccoli-blind
GitHub stars
285
Token cost
~2.2k tokens
SKILL.md length
495 words
Files
2 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Non-interactive wrapper: plan-sketch - auto-pick recommended options - plan-write - plan-critique-loop - implement-from-plan - claude-simplify-wrapper - dedup - code-review-loop.

  • Works in 12 steps: Prepare subagent logs and heartbeat → Write IDEA_FILE from user input → Run plan-sketch and auto-select… → …
  • Tasks that involve Code review
  • SKILL.md covers Preconditions, Required subskills and Workflow
  • Runs Python scripts from its folder; calls git and python3

What it does

Besimple Broccoli Blind is an agent skill from besimple-oss/broccoli. Non-interactive wrapper: plan-sketch - auto-pick recommended options - plan-write - plan-critique-loop - implement-from-plan - claude-simplify-wrapper - dedup - code-review-loop. No PR creation and no Linear comments.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/prepare_plan_write_input.py`).

It sits in Development, covering Code review. The repository describes itself as: Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers. The licence is MIT.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/besimple-broccoli-blind”

Requirements

  • Python 3

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Prepare subagent logs and heartbeat
  2. Write IDEA_FILE from user input
  3. Run plan-sketch and auto-select recommended options
  4. Create working branch
  5. Build plan-write input
  6. Run plan-write and commit plan
  7. Run plan-critique-loop
  8. Commit plan updates (if changed)
  9. Git hygiene
  10. Implement from plan (inline)
  11. Run simplify loop
  12. Run dedup loop

What it can do on your machine

Read from SKILL.md and the folder at commit 6cad3b9. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • python3

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Besimple Broccoli Blind loads about 2.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 495 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
~2.2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from besimple-oss/broccoli at commit 6cad3b9, republished under its MIT licence (© besimple-oss). 495 words, ~2,172 tokens.

Download SKILL.mdSave it as .claude/skills/besimple-broccoli-blind/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
besimple-broccoli-blind
description
Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.

Sketch -> Auto-select -> Plan -> Critique -> Implement -> Simplify -> Dedup -> Review (blind wrapper)

This is the automation-safe variant of besimple-broccoli.

  • It uses the same planning + implementation flow.
  • It automatically chooses recommended clarification options.
  • It does not open PRs and does not post Linear comments.

Preconditions

  • Confirm repo: git rev-parse --show-toplevel
  • Ensure CLIs: codex, claude
  • Ensure git commits are possible (user.name / user.email configured)

Required subskills

  • plan-sketch
  • plan-write
  • plan-critique-loop
  • implement-from-plan
  • claude-simplify-wrapper
  • dedup
  • code-review-loop

Workflow

  1. Prepare subagent logs and heartbeat

    bash
    LOG_DIR="/tmp/codex-subagent-logs/$(basename "$PWD")"
    HEARTBEAT_SECONDS=60
    SUBAGENT_TIMEOUT_SECONDS=7200
    mkdir -p "${LOG_DIR}"
    SKETCH_LOG="${LOG_DIR}/plan-sketch.log"
    WRITE_LOG="${LOG_DIR}/plan-write.log"
    CRITIQUE_LOG="${LOG_DIR}/plan-critique.log"
    SIMPLIFY_LOG="${LOG_DIR}/simplify.log"
    DEDUP_LOG="${LOG_DIR}/dedup.log"
    REVIEW_LOG="${LOG_DIR}/code-review.log"
    : > "${SKETCH_LOG}"
    : > "${WRITE_LOG}"
    : > "${CRITIQUE_LOG}"
    : > "${SIMPLIFY_LOG}"
    : > "${DEDUP_LOG}"
    : > "${REVIEW_LOG}"

    Resolve installed skill directories (so the wrapper works from any repo):

    bash
    resolve_skill_dir() {
      local name="$1"
      local repo_root=""
      repo_root="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
    
      local candidates=(
        "$repo_root/.agents/skills/$name"
        "$repo_root/.claude/skills/$name"
        "$HOME/.agents/skills/$name"
        "$HOME/.codex/skills/$name"
        "$HOME/.claude/skills/$name"
      )
    
      for d in "${candidates[@]}"; do
        if [[ -d "$d" ]]; then
          echo "$d"
          return 0
        fi
      done
    
      echo "Error: skill '$name' not found in repo-scoped or user-scoped skill dirs." >&2
      return 1
    }
    
    BESIMPLE_BROCCOLI_BLIND_SKILL_DIR="$(resolve_skill_dir besimple-broccoli-blind)"
    PLAN_SKETCH_SKILL_DIR="$(resolve_skill_dir plan-sketch)"
    PLAN_WRITE_SKILL_DIR="$(resolve_skill_dir plan-write)"
    PLAN_CRITIQUE_LOOP_SKILL_DIR="$(resolve_skill_dir plan-critique-loop)"
    SIMPLIFY_SKILL_DIR="$(resolve_skill_dir claude-simplify-wrapper)"
    DEDUP_SKILL_DIR="$(resolve_skill_dir dedup)"
    CODE_REVIEW_LOOP_SKILL_DIR="$(resolve_skill_dir code-review-loop)"
  2. Write IDEA_FILE from user input

    • IDEA_FILE="${LOG_DIR}/idea.md"
    • Preserve the user message verbatim.
  3. Run plan-sketch and auto-select recommended options

    bash
    SKETCH_DOC=$(python3 "$PLAN_SKETCH_SKILL_DIR/scripts/run_plan_sketch.py" --idea-file "${IDEA_FILE}" --output "${LOG_DIR}/sketch.md" --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${SKETCH_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}")

    Extract the last user-questions block:

    bash
    QUESTIONS_BLOCK=$(awk '
      /^BEGIN_USER_QUESTIONS$/ {in_block=1; block=""; next}
      /^END_USER_QUESTIONS$/   {in_block=0; last=block; next}
      in_block                 {block = block $0 ORS}
      END                      {printf "%s", last}
    ' "${SKETCH_LOG}")

    Auto-pick recommended options by reading QUESTIONS_BLOCK directly in the LLM context (no shell/regex parsing):

    • Set AUTO_SELECTIONS to a comma-separated list of all labels whose option text ends with (Recommended) (for example: 1a, 2c).
    • Do not compute AUTO_SELECTIONS with awk, jq, or python.
    • If no recommended options are present, continue to empty feedback.

    Save synthetic feedback:

    bash
    USER_FEEDBACK_FILE="${LOG_DIR}/user-feedback.md"
    cat > "${USER_FEEDBACK_FILE}" <<'FEEDBACK'

User feedback (verbatim)

<auto-populated by wrapper>
FEEDBACK
   printf "%s\n" "${AUTO_SELECTIONS}" >> "${USER_FEEDBACK_FILE}"
   ```

Append to IDEA_FILE:

  • Clarification mode: automatic recommended picks
  • Selected labels: ${AUTO_SELECTIONS}
  1. Create working branch

    • Ensure clean tree:
      bash
      if [ -n "$(git status --porcelain)" ]; then
        echo "Working tree is not clean. Aborting before branch creation." >&2
        exit 1
      fi
    • Choose BASE_REF explicitly:
      • If the user explicitly asked for a base branch/commit in the request, use that.
      • Otherwise, derive the default remote branch:
        bash
        DEFAULT_BRANCH="$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null | sed 's#^origin/##')"
        if [ -z "${DEFAULT_BRANCH}" ]; then
          if git show-ref --verify --quiet refs/remotes/origin/main; then DEFAULT_BRANCH=main;
          elif git show-ref --verify --quiet refs/remotes/origin/master; then DEFAULT_BRANCH=master;
          else
            echo "Could not determine origin default branch (origin/HEAD, main, master). Aborting." >&2
            exit 1
          fi
        fi
        BASE_REF="origin/${DEFAULT_BRANCH}"
    • Choose branch name explicitly from clarified scope:
      • Use task/ prefix.
      • Build a short slug from the clarified goal in IDEA_FILE (letters/numbers/dashes only, concise and specific).
      • Example: task/auto-select-recommended-options.
    • Sanitize, avoid collisions, and create the branch:
      bash
      BRANCH_NAME_SEED="task/<clarified-scope-slug>"
      BRANCH_NAME="${BRANCH_NAME_SEED}"
      BRANCH_NAME="$(echo "${BRANCH_NAME}" | tr '[:upper:]' '[:lower:]' | sed -E 's@[^a-z0-9._/-]+@-@g; s@/+@/@g; s@^-+@@; s@-+$@@; s@^/+@@; s@/+$@@')"
      if [ -z "${BRANCH_NAME}" ]; then
        echo "Branch name is empty after sanitization. Aborting." >&2
        exit 1
      fi
      BRANCH="${BRANCH_NAME}"
      if git show-ref --verify --quiet "refs/heads/${BRANCH}"; then
        i=2
        while git show-ref --verify --quiet "refs/heads/${BRANCH}-${i}"; do i=$((i+1)); done
        BRANCH="${BRANCH}-${i}"
      fi
      if ! git rev-parse --verify --quiet "${BASE_REF}^{commit}" >/dev/null; then
        echo "Base ref does not resolve to a commit: ${BASE_REF}. Aborting." >&2
        exit 1
      fi
      git checkout -b "${BRANCH}" "${BASE_REF}"
  2. Build plan-write input

    bash
    PLAN_WRITE_INPUT="${LOG_DIR}/plan-write-input.md"
    python3 "$BESIMPLE_BROCCOLI_BLIND_SKILL_DIR/scripts/prepare_plan_write_input.py" \
      --sketch-doc "${SKETCH_DOC}" \
      --sketch-log "${SKETCH_LOG}" \
      --user-feedback "${USER_FEEDBACK_FILE}" \
      --output "${PLAN_WRITE_INPUT}"
  3. Run plan-write and commit plan

    bash
    PLAN_DOC=$(python3 "$PLAN_WRITE_SKILL_DIR/scripts/run_plan_write.py" "${PLAN_WRITE_INPUT}" --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${WRITE_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}")
    git add "${PLAN_DOC}"
    git commit -m "Plan: initial draft"
  4. Run plan-critique-loop

    bash
    python3 "$PLAN_CRITIQUE_LOOP_SKILL_DIR/scripts/run_critique_loop.py" "${PLAN_DOC}" --max-iterations 2 --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${CRITIQUE_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}"
  5. Commit plan updates (if changed)

    bash
    git add "${PLAN_DOC}"
    git diff --cached --quiet || git commit -m "Plan critique: updates"
  6. Git hygiene

    • Ensure codex-progress.log is ignored and untracked
    • Ensure clean tree
    • Record REVIEW_BASE_SHA=$(git rev-parse HEAD)
  7. Implement from plan (inline)

    • Run implement-from-plan subskill with PLAN_DOC
  8. Run simplify loop

    bash
    python3 "$SIMPLIFY_SKILL_DIR/scripts/run_simplify_loop.py" "${REVIEW_BASE_SHA}" --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${SIMPLIFY_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}"
  9. Run dedup loop

    bash
    python3 "$DEDUP_SKILL_DIR/scripts/run_dedup_loop.py" "${REVIEW_BASE_SHA}" --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${DEDUP_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}"
  10. Run review loop

    bash
    python3 "$CODE_REVIEW_LOOP_SKILL_DIR/scripts/run_review_loop.py" "${REVIEW_BASE_SHA}" --max-iterations 2 --timeout "${SUBAGENT_TIMEOUT_SECONDS}" --progress-log "${REVIEW_LOG}" --heartbeat-seconds "${HEARTBEAT_SECONDS}"
  11. Stop

    • Do not open a PR.
    • Do not post Linear comments.
    • Leave branch/PR/comments to external automation worker.

© besimple-oss, MIT. 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 (scripts) in prompt-templates/skills/besimple-broccoli-blind of besimple-oss/broccoli.

  • SKILL.md
  • scripts/prepare_plan_write_input.py

Open the folder on GitHubat commit 6cad3b9

Compare with similar skills

Besimple Broccoli Blind 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.

Besimple Broccoli Blind compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Besimple Broccoli Blind this skillbesimple-oss/broccoli285—~2.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

Similar skills

  • 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 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from besimple-oss/broccoli

All 10 skills in this repo
  • Broccoli Oss GCP Deploy

    besimple-oss/broccoli

    Deploy this repository to a new Google Cloud project using the repo's existing Cloud Run, Cloud Run Jobs, Cloud SQL, Secret Manager, and Artifact Registry scripts.

    285 GitHub stars~4.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Plan Critique Loop

    besimple-oss/broccoli

    Critique and revise an existing plan doc up to 3 iterations, using accept/reject triage and stopping early when no important feedback remains.

    285 GitHub stars~1.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Plan Sketch

    besimple-oss/broccoli

    Do bounded research (official docs first) and produce a high-level implementation sketch in sketch/<generated-name.md.

    285 GitHub stars~1.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Plan Write

    besimple-oss/broccoli

    Write a detailed, self-contained implementation plan to a new Markdown file under plan/.

    285 GitHub stars~721 tokensUpdated 5 mo ago
    Auto-check passed
  • Claude Simplify Wrapper

    besimple-oss/broccoli

    Run Claude's built-in /simplify skill on BASESHA..HEAD, validate checks, and commit.

    285 GitHub stars~1.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Code Review Loop

    besimple-oss/broccoli

    Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.

    285 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed

Categories

Questions about Besimple Broccoli Blind

What does Besimple Broccoli Blind do?

Non-interactive wrapper: plan-sketch - auto-pick recommended options - plan-write - plan-critique-loop - implement-from-plan - claude-simplify-wrapper - dedup - code-review-loop. Besimple Broccoli Blind is an agent skill from besimple-oss/broccoli. Non-interactive wrapper: plan-sketch - auto-pick recommended options - plan-write - plan-critique-loop - implement-from-plan - claude-simplify-wrapper - dedup - code-review-loop.

When should I use Besimple Broccoli Blind?

Besimple Broccoli Blind fits situations like: tasks that involve Code review.

How do I install Besimple Broccoli Blind in Claude Code?

Run `npx skills add besimple-oss/broccoli --skill besimple-broccoli-blind -a claude-code`. Or copy the skill folder (prompt-templates/skills/besimple-broccoli-blind in besimple-oss/broccoli) into .claude/skills/besimple-broccoli-blind in your project. Claude Code loads it when a task matches its description.

How do I install Besimple Broccoli Blind in Codex?

Run `npx skills add besimple-oss/broccoli --skill besimple-broccoli-blind -a codex`. Or copy the skill folder (prompt-templates/skills/besimple-broccoli-blind in besimple-oss/broccoli) into .agents/skills/besimple-broccoli-blind in your project. Codex loads it when a task matches its description.

Can I use Besimple Broccoli Blind 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 besimple-oss/broccoli --skill besimple-broccoli-blind -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/besimple-broccoli-blind, .gemini/skills/besimple-broccoli-blind, .github/skills/besimple-broccoli-blind and .opencode/skills/besimple-broccoli-blind in your project.

What does Besimple Broccoli Blind need to run?

Going by SKILL.md and its folder, Besimple Broccoli Blind needs Python for the scripts in its folder and the command-line tools its instructions call (git and python3). Our summary lists: Python 3.

Does Besimple Broccoli Blind access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Besimple Broccoli Blind 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Besimple Broccoli Blind use?

Besimple Broccoli Blind is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Besimple Broccoli Blind use?

About 2.2k tokens (SKILL.md is roughly 8.7k 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 Besimple Broccoli Blind?

Skills that share tags, products or a category with Besimple Broccoli Blind: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Besimple Broccoli Blind?

besimple-oss (a GitHub organization) maintains it in besimple-oss/broccoli, which has 285 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on April 26, 2026.

Source: besimple-oss/broccoli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.