Catalog
affaan-m/blueprint

affaan-m

blueprint

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

global
0installs0uses~1.3k
v1.1Saved Apr 20, 2026

Blueprint — Construction Plan Generator

Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold.

When to Use

  • Breaking a large feature into multiple PRs with clear dependency order
  • Planning a refactor or migration that spans multiple sessions
  • Coordinating parallel workstreams across sub-agents
  • Any task where context loss between sessions would cause rework

Do not use for tasks completable in a single PR, fewer than 3 tool calls, or when the user says "just do it."

How It Works

Blueprint runs a 5-phase pipeline:

  1. Research — Pre-flight checks (git, gh auth, remote, default branch), then reads project structure, existing plans, and memory files to gather context.
  2. Design — Breaks the objective into one-PR-sized steps (3–12 typical). Assigns dependency edges, parallel/serial ordering, model tier (strongest vs default), and rollback strategy per step.
  3. Draft — Writes a self-contained Markdown plan file to plans/. Every step includes a context brief, task list, verification commands, and exit criteria — so a fresh agent can execute any step without reading prior steps.
  4. Review — Delegates adversarial review to a strongest-model sub-agent (e.g., Opus) against a checklist and anti-pattern catalog. Fixes all critical findings before finalizing.
  5. Register — Saves the plan, updates memory index, and presents the step count and parallelism summary to the user.

Blueprint detects git/gh availability automatically. With git + GitHub CLI, it generates full branch/PR/CI workflow plans. Without them, it switches to direct mode (edit-in-place, no branches).

Examples

Basic usage

/blueprint myapp "migrate database to PostgreSQL"

Produces plans/myapp-migrate-database-to-postgresql.md with steps like:

  • Step 1: Add PostgreSQL driver and connection config
  • Step 2: Create migration scripts for each table
  • Step 3: Update repository layer to use new driver
  • Step 4: Add integration tests against PostgreSQL
  • Step 5: Remove old database code and config

Multi-agent project

/blueprint chatbot "extract LLM providers into a plugin system"

Produces a plan with parallel steps where possible (e.g., "implement Anthropic plugin" and "implement OpenAI plugin" run in parallel after the plugin interface step is done), model tier assignments (strongest for the interface design step, default for implementation), and invariants verified after every step (e.g., "all existing tests pass", "no provider imports in core").

Key Features

  • Cold-start execution — Every step includes a self-contained context brief. No prior context needed.
  • Adversarial review gate — Every plan is reviewed by a strongest-model sub-agent against a checklist covering completeness, dependency correctness, and anti-pattern detection.
  • Branch/PR/CI workflow — Built into every step. Degrades gracefully to direct mode when git/gh is absent.
  • Parallel step detection — Dependency graph identifies steps with no shared files or output dependencies.
  • Plan mutation protocol — Steps can be split, inserted, skipped, reordered, or abandoned with formal protocols and audit trail.
  • Zero runtime risk — Pure Markdown skill. The entire repository contains only .md files — no hooks, no shell scripts, no executable code, no package.json, no build step. Nothing runs on install or invocation beyond Claude Code's native Markdown skill loader.

Installation

This skill ships with Everything Claude Code. No separate installation is needed when ECC is installed.

Full ECC install

If you are working from the ECC repository checkout, verify the skill is present with:

test -f skills/blueprint/SKILL.md

To update later, review the ECC diff before updating:

cd /path/to/everything-claude-code
git fetch origin main
git log --oneline HEAD..origin/main       # review new commits before updating
git checkout <reviewed-full-sha>          # pin to a specific reviewed commit

Vendored standalone install

If you are vendoring only this skill outside the full ECC install, copy the reviewed file from the ECC repository into ~/.claude/skills/blueprint/SKILL.md. Vendored copies do not have a git remote, so update them by re-copying the file from a reviewed ECC commit rather than running git pull.

Requirements

  • Claude Code (for /blueprint slash command)
  • Git + GitHub CLI (optional — enables full branch/PR/CI workflow; Blueprint detects absence and auto-switches to direct mode)

Source

Inspired by antbotlab/blueprint — upstream project and reference design.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

B

Good

Safety

88

Quality

72

Clarity

78

Completeness

68

Summary

Blueprint is a planning skill that converts high-level objectives into detailed step-by-step construction plans for multi-session engineering projects. It runs a 5-phase pipeline (Research, Design, Draft, Review, Register) to produce self-contained, cold-start-executable Markdown plans with dependency graphs, parallel step detection, and adversarial review gates. The skill itself is pure Markdown with no executable code, shell scripts, or runtime hooks.

Detected Capabilities

Parse user objectives and translate into phased execution plansAnalyze project structure and detect git/GitHub CLI availabilityGenerate dependency graphs and identify parallel execution opportunitiesAssign model tier (strongest vs default) per step based on complexityWrite self-contained step context briefs for cold-start agent executionDelegate adversarial plan review to strongest-model sub-agentsSupport branch/PR/CI workflow generation with graceful degradation to direct modeDocument plan mutation protocols (split, insert, skip, reorder, abandon steps)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

plan multi-session projectbreak feature into PRsmulti-agent roadmapcomplex refactor planningdependency graph design

Risk Signals

INFO

Delegates sub-agent execution to strongest-model AI (e.g., Opus) for adversarial review

Design & Review phases, general description
INFO

Reads project structure, memory files, and existing plans during Research phase

Research phase description
INFO

Writes Markdown plan files to `plans/` directory

Draft phase description
INFO

Detects git/GitHub CLI and generates branch/PR/CI workflows or switches to direct mode

How It Works section

Use Cases

  • Break large features into multiple PRs with clear dependency order
  • Plan multi-session refactors or migrations spanning weeks of work
  • Coordinate parallel workstreams across sub-agents with defined interfaces
  • Generate construction roadmaps for complex systems where context loss between sessions would cause rework
  • Design plugin systems, major architectural changes, or multi-team initiatives

Quality Notes

  • Well-structured documentation with clear phase descriptions and realistic examples
  • Explicit trigger conditions and anti-trigger conditions help users understand when the skill applies
  • Examples show concrete outputs and multi-agent coordination patterns
  • Installation section addresses both full ECC and vendored standalone deployments
  • Explicitly documents zero runtime risk and pure-Markdown design
  • Skill scope is narrowly bounded to planning, not execution — reduces blast radius
  • Graceful degradation pattern (git/gh optional, auto-switches to direct mode) shows thoughtful design
  • The skill references 'antbotlab/blueprint' as upstream but does not include implementation details or code samples for the 5-phase pipeline — readers must infer how each phase works
  • No explicit error handling guidance for edge cases (e.g., what if project has no git, memory files are corrupted, or user provides ambiguous objective)
  • Plan mutation protocol is mentioned but not documented with examples or formal procedures
  • Anti-pattern catalog is referenced in Review phase but not enumerated or described
Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest
v1.0

Seeded from github.com/affaan-m/everything-claude-code

2026-03-16

Add affaan-m/blueprint to your library

Command Palette

Search for a command to run...