Evaluate-Loop Step 1: PLAN. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

AGPL-3.0Auto-check: notesProduct & Project Management

Install Loop Planner

skills CLI
$ npx skills add Ibrahim-3d/orchestrator-supaconductor --skill loop-planner -a claude-code

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

GitHub CLI
$ gh skill install Ibrahim-3d/orchestrator-supaconductor loop-planner --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/Ibrahim-3d/orchestrator-supaconductor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-planner .claude/skills/loop-planner && 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
loop-planner
GitHub stars
380
Token cost
~2.3k tokens
SKILL.md length
474 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Evaluate-Loop Step 1: PLAN. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

  • Works in 4 steps: Load Context → Identify Scope Boundaries → Create Phased Plan with DAG → …
  • Tasks that involve User stories
  • SKILL.md covers Inputs Required, Workflow, Phase 1: [Phase Name] and Phase 2: [Phase Name], plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Loop Planner is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Evaluate-Loop Step 1: PLAN. Use this agent when starting a new track or feature to create a detailed execution plan. Reads spec.md, loads project context, and produces a phased plan.md with specific tasks, acceptance criteria, and dependencies. Triggered by: 'plan feature', 'create plan', 'start track', '/conductor implement' (planning phase).

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering User stories. The repository describes itself as: Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve User stories

Example prompts

  • “plan feature”
  • “create plan”
  • “start track”
  • “/loop-planner”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Load Context
  2. Identify Scope Boundaries
  3. Create Phased Plan with DAG
  4. Output

What it can do on your machine

Read from SKILL.md and the folder at commit 76c9b10. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and json).

    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

Loop Planner loads about 2.3k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:243
    | `config`, `.json`, `.env` | `config` |

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 Ibrahim-3d/orchestrator-supaconductor at commit 76c9b10, republished under its AGPL-3.0 licence (© Ibrahim-3d). 474 words, ~2,347 tokens.

Download SKILL.mdSave it as .claude/skills/loop-planner/SKILL.md (or your agent's skills folder).
name
loop-planner
description
Evaluate-Loop Step 1: PLAN. Use this agent when starting a new track or feature to create a detailed execution plan. Reads spec.md, loads project context, and produces a phased plan.md with specific tasks, acceptance criteria, and dependencies. Triggered by: 'plan feature', 'create plan', 'start track', '/conductor implement' (planning phase).

Loop Planner Agent — Step 1: PLAN

Creates detailed, scoped execution plans for tracks. This is Step 1 of the Evaluate-Loop.

Inputs Required

  1. Track spec.md — what needs to be built
  2. conductor/tracks.md — what's already been done (to avoid overlap)
  3. Track plan.md (if exists) — check for prior progress

Workflow

1. Load Context

read_file in order:

  1. conductor/tracks.md — completed tracks and their deliverables
  2. Track's spec.md — requirements for this track
  3. Track's plan.md (if exists) — check what's already [x] done
  4. conductor/product.md — product scope reference
  5. conductor/tech-stack.md — technical constraints
2. Identify Scope Boundaries

Before writing any plan:

  • List what spec.md asks for (deliverables)
  • List what's already done in other tracks (from tracks.md)
  • Identify overlap — anything in spec that was already delivered elsewhere
  • Flag overlap items as "SKIP — already done in [TRACK-ID]"
3. Create Phased Plan with DAG

write_file plan.md with this structure (now includes dependency DAG for parallel execution):

markdown
# [Track Name] — Execution Plan

## Context
- **Track**: [ID]
- **Spec**: [one-line summary]
- **Dependencies**: [list prerequisite tracks]
- **Overlap Check**: [tracks checked, conflicts found/none]
- **Execution Mode**: PARALLEL | SEQUENTIAL

## Dependency Graph

<!-- YAML DAG for parallel execution -->
```yaml
dag:
  nodes:
    - id: "1.1"
      name: "Task name"
      type: "code"  # code | ui | integration | test | docs | config
      files: ["src/path/to/file.ts"]
      depends_on: []
      estimated_duration: "30m"
      phase: 1
    - id: "1.2"
      name: "Another task"
      type: "code"
      files: ["src/another/file.ts"]
      depends_on: []
      phase: 1
    - id: "1.3"
      name: "Depends on 1.1 and 1.2"
      type: "code"
      files: ["src/path/to/file.ts"]
      depends_on: ["1.1", "1.2"]
      phase: 1

  parallel_groups:
    - id: "pg-1"
      tasks: ["1.1", "1.2"]
      conflict_free: true
    - id: "pg-2"
      tasks: ["1.3", "1.4"]
      conflict_free: false
      shared_resources: ["src/path/to/file.ts"]
      coordination_strategy: "file_lock"

Phase 1: [Phase Name]

Tasks
  • Task 1.1: [Specific action] <!-- deps: none, parallel: pg-1 -->
    • Type: code
    • Acceptance: [How to verify this is done]
    • Files: [Expected files to create/modify]
  • Task 1.2: [Specific action] <!-- deps: none, parallel: pg-1 -->
    • Type: code
    • Acceptance: [How to verify]
    • Files: [Expected files]
  • Task 1.3: [Depends on above] <!-- deps: 1.1, 1.2 -->
    • Type: code
    • Acceptance: [How to verify]
    • Files: [Expected files]

Phase 2: [Phase Name]

...

Discovered Work

<!-- Add items here during execution if scope expansion is needed -->

### 3.1 DAG Generation Algorithm

When creating the plan, build the dependency graph:

```python
def generate_dag(tasks: list) -> dict:
    """
    Generate DAG from task list.

    1. Create nodes for each task
    2. Analyze dependencies (explicit + file-based)
    3. Identify parallel groups (tasks at same level with no conflicts)
    4. Detect shared resources
    """

    nodes = []
    for task in tasks:
        nodes.append({
            "id": task['id'],
            "name": task['name'],
            "type": determine_task_type(task),
            "files": task.get('files', []),
            "depends_on": task.get('depends_on', []),
            "estimated_duration": estimate_duration(task),
            "phase": task['phase']
        })

    # Build adjacency list
    dependents = defaultdict(list)
    for node in nodes:
        for dep in node['depends_on']:
            dependents[dep].append(node['id'])

    # Compute topological levels
    levels = compute_topological_levels(nodes)

    # Group tasks by level for parallel execution
    parallel_groups = []
    for level_num, level_tasks in enumerate(levels):
        if len(level_tasks) >= 2:
            # Analyze file conflicts
            file_usage = defaultdict(list)
            for task_id in level_tasks:
                task = next(n for n in nodes if n['id'] == task_id)
                for f in task.get('files', []):
                    file_usage[f].append(task_id)

            # Find conflict-free groups
            shared_files = {f: tasks for f, tasks in file_usage.items() if len(tasks) > 1}

            if not shared_files:
                parallel_groups.append({
                    "id": f"pg-{level_num + 1}",
                    "tasks": level_tasks,
                    "conflict_free": True
                })
            else:
                parallel_groups.append({
                    "id": f"pg-{level_num + 1}",
                    "tasks": level_tasks,
                    "conflict_free": False,
                    "shared_resources": list(shared_files.keys()),
                    "coordination_strategy": "file_lock"
                })

    return {
        "nodes": nodes,
        "parallel_groups": parallel_groups
    }
3.2 Bite-Sized Task Format

Each task MUST follow the TDD bite-sized format. Every task is one focused action (2-5 minutes) with exact file paths and complete code:

markdown
### Task 1.1: [Component Name]

**Files:**
- Create: `exact/path/to/file.ts`
- Modify: `exact/path/to/existing.ts:123-145`
- Test: `tests/exact/path/to/test.ts`

**Step 1: Write the failing test**

```typescript
test('specific behavior', () => {
    const result = function(input);
    expect(result).toBe(expected);
});
```

**Step 2: Run test to verify it fails**

Run: `npm test -- --grep "specific behavior"`
Expected: FAIL with "function not defined"

**Step 3: Write minimal implementation**

```typescript
export function specificFunction(input: string): string {
    return expected;
}
```

**Step 4: Run test to verify it passes**

Run: `npm test -- --grep "specific behavior"`
Expected: PASS

**Step 5: Commit**

```bash
git add tests/path/test.ts src/path/file.ts
git commit -m "feat: add specific feature"
```

Key rules:

  • Exact file paths always — no "add to the appropriate file"
  • Complete code in plan — not "add validation" or "implement logic"
  • Exact commands with expected output
  • DRY, YAGNI, TDD, frequent commits
Show full SKILL.md (211 more words)Show less
3.3 Task Type Detection

Automatically detect task type from description and files:

IndicatorsType
src/components/, .tsx, ui, componentui
api/, integration, supabase, stripeintegration
.test.ts, test, coveragetest
.md, docs, documentationdocs
config, .json, .envconfig
Defaultcode
3.4 Parallel Group Identification

Tasks can run in parallel if:

  1. No dependency relationship (neither depends on the other)
  2. At the same topological level
  3. Either:
    • No shared files (conflict_free: true)
    • Shared files with coordination strategy (conflict_free: false)
3.5 Plan Quality Checklist

Before finalizing, verify:

CheckQuestion
ScopedDoes every task trace back to a spec.md requirement?
No OverlapDoes any task duplicate work from completed tracks?
TestableDoes every task have clear acceptance criteria?
OrderedAre tasks sequenced by dependency?
SizedCan each task be completed in a single session?
4. Output

Save the plan to the track's plan.md and report:

## Plan Created

**Track**: [track-id]
**Phases**: [count]
**Tasks**: [total count]
**Dependencies**: [list]
**Ready for**: Step 2 (Evaluate Plan) → hand off to loop-plan-evaluator

Metadata Checkpoint Updates

The planner MUST update the track's metadata.json at key points:

On Start
json
{
  "loop_state": {
    "current_step": "PLAN",
    "step_status": "IN_PROGRESS",
    "step_started_at": "[ISO timestamp]",
    "checkpoints": {
      "PLAN": {
        "status": "IN_PROGRESS",
        "started_at": "[ISO timestamp]",
        "agent": "loop-planner"
      }
    }
  }
}
On Completion
json
{
  "loop_state": {
    "current_step": "EVALUATE_PLAN",
    "step_status": "NOT_STARTED",
    "checkpoints": {
      "PLAN": {
        "status": "PASSED",
        "started_at": "[start timestamp]",
        "completed_at": "[ISO timestamp]",
        "agent": "loop-planner",
        "commit_sha": "[if plan was committed]",
        "plan_version": 1
      },
      "EVALUATE_PLAN": {
        "status": "NOT_STARTED"
      }
    }
  }
}
Update Protocol
  1. read_file current metadata.json
  2. Update loop_state.checkpoints.PLAN fields
  3. Advance current_step to EVALUATE_PLAN
  4. write_file back to metadata.json

If metadata.json doesn't exist or is v1 format, create v2 structure with default values.

Handoff

After creating the plan, the Conductor should dispatch the loop-plan-evaluator agent to verify the plan before execution begins.

© Ibrahim-3d, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/loop-planner of Ibrahim-3d/orchestrator-supaconductor.

Open the folder on GitHubat commit 76c9b10

Compare with similar skills

Loop Planner 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.

Loop Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loop Planner this skillIbrahim-3d/orchestrator-supaconductor380—~2.3kAutomated safety check: NotesAGPL-3.0
Project Planneradrianpuiu/claude-skills-marketplace1001 repos~6kAutomated safety check: PassNone
Sdd Work Decompositionmagnus919/hermes-profiles278—~1.4kAutomated safety check: PassMIT
Feature ForgeJeffallan/claude-skills12k—~1.1kAutomated safety check: PassMIT
Refactor Design Reportpenwyp/ClaudePreference136—~1.4kAutomated safety check: PassMIT
Spec WorkflowTencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Project Planner

    adrianpuiu/claude-skills-marketplace

    Comprehensive project planning and documentation generator for software projects.

    100 GitHub starsUsed in 1 repo~6k tokens
    Product & Project ManagementAuto-check passed
  • Sdd Work Decomposition

    magnus919/hermes-profiles

    SDD work decomposition — translates formal specifications into dependency-aware task plans with per-task acceptance criteria.

    278 GitHub stars~1.4k tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check passed
  • Feature Forge

    Jeffallan/claude-skills

    Runs a structured requirements interview to produce a feature specification with EARS requirements, acceptance criteria and an implementation checklist.

    12k GitHub stars~1.1k tokensUpdated 4 days ago
    Product & Project ManagementAuto-check passed
  • Refactor Design Report

    penwyp/ClaudePreference

    Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…

    136 GitHub stars~1.4k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Spec Workflow

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance…

    1.1k GitHub starsUsed in 2 repos~1.3k tokens
    Product & Project ManagementAuto-check passed
  • Cas Supervisor Checklist

    codingagentsystem/cas

    Quick startup checklist for factory supervisors. An agent skill from codingagentsystem/cas.

    176 GitHub stars~349 tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

More from Ibrahim-3d/orchestrator-supaconductor

All 27 skills in this repo
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    380 GitHub starsUsed in 4 repos~2.4k tokens
    Auto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    380 GitHub starsUsed in 8 repos~2.9k tokens
    Auto-check passed
  • Agent Factory

    Ibrahim-3d/orchestrator-supaconductor

    Creates specialized worker agents dynamically from templates.

    380 GitHub stars~2.9k tokensUpdated 9 days ago
    Auto-check passed
  • Board Of Directors

    Ibrahim-3d/orchestrator-supaconductor

    Simulate a 5-member expert board deliberation for major decisions.

    380 GitHub stars~1.9k tokensUpdated 9 days ago
    Auto-check passed
  • Business Docs Sync

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when completing a track that changes pricing, AI models, product features, or asset pipelines — syncs business context documents across all tiers.

    380 GitHub stars~2.1k tokensUpdated 9 days ago
    Auto-check passed
  • Context Loader

    Ibrahim-3d/orchestrator-supaconductor

    Load project context efficiently for Conductor workflows. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

    380 GitHub stars~830 tokensUpdated 9 days ago
    Auto-check passed

Questions about Loop Planner

What does Loop Planner do?

Evaluate-Loop Step 1: PLAN. An agent skill from Ibrahim-3d/orchestrator-supaconductor. Loop Planner is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Evaluate-Loop Step 1: PLAN.

When should I use Loop Planner?

Loop Planner fits situations like: tasks that involve User stories.

How do I install Loop Planner in Claude Code?

Run `npx skills add Ibrahim-3d/orchestrator-supaconductor --skill loop-planner -a claude-code`. Or copy the skill folder (skills/loop-planner in Ibrahim-3d/orchestrator-supaconductor) into .claude/skills/loop-planner in your project. Claude Code loads it when a task matches its description.

How do I install Loop Planner in Codex?

Run `npx skills add Ibrahim-3d/orchestrator-supaconductor --skill loop-planner -a codex`. Or copy the skill folder (skills/loop-planner in Ibrahim-3d/orchestrator-supaconductor) into .agents/skills/loop-planner in your project. Codex loads it when a task matches its description.

Can I use Loop Planner 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 Ibrahim-3d/orchestrator-supaconductor --skill loop-planner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-planner, .gemini/skills/loop-planner, .github/skills/loop-planner and .opencode/skills/loop-planner in your project.

What does Loop Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Loop Planner is instructions for the agent only. Our summary lists: Python 3.

Does Loop Planner 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 Loop Planner safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Loop Planner use?

Loop Planner is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Loop Planner use?

About 2.3k tokens (SKILL.md is roughly 9.4k 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 Loop Planner?

Skills that share tags, products or a category with Loop Planner: Project Planner (adrianpuiu/claude-skills-marketplace, 100 stars), Sdd Work Decomposition (magnus919/hermes-profiles, 278 stars), Feature Forge (Jeffallan/claude-skills, 12k stars) and Refactor Design Report (penwyp/ClaudePreference, 136 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loop Planner?

Ibrahim-3d (a GitHub user) maintains it in Ibrahim-3d/orchestrator-supaconductor, which has 380 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 27, 2026.

Source: Ibrahim-3d/orchestrator-supaconductor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.