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
origin:community
New~1.3k
v1.2Saved Jul 14, 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

82/100

Grade

B

Good

Safety

88

Quality

84

Clarity

86

Completeness

73

Summary

Blueprint is a planning and orchestration skill that transforms a one-line project objective into a detailed, multi-step construction plan for complex engineering work. It runs a 5-phase pipeline (Research → Design → Draft → Review → Register) that breaks large tasks into PR-sized chunks, generates self-contained Markdown step documents, performs adversarial review, and detects parallelizable work. The skill is purely documentation-focused with no executable code, shell scripts, or runtime installation artifacts.

Detected Capabilities

read git metadataread project structureread memory filesread existing planswrite markdown plan filesperform adversarial review via sub-agent delegationdependency graph analysisparallel task detectionplan mutation and audit trail

Trigger Keywords

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

multi-pr roadmapbreak down large tasksplan database migrationdesign parallel architecturemulti-session project planning

Use Cases

  • Breaking large features into multi-PR roadmaps with clear dependency order
  • Planning database migrations, refactors, or system redesigns across multiple sessions
  • Coordinating parallel workstreams and sub-agent execution paths
  • Documenting complex project timelines where context loss between sessions causes rework
  • Designing plugin systems or modular architecture with parallel implementation tracks

Quality Notes

  • Excellent scope clarity: explicitly states when NOT to use (single-PR tasks, <3 tool calls, 'just do it')
  • Strong structural documentation with clear 5-phase pipeline and decision flow
  • Degradation mode (git/gh → direct mode) is well-articulated, reducing brittleness
  • Comprehensive examples (basic and multi-agent) show expected output and use cases
  • Clear guardrail: no executable code, no hooks, no shell scripts, pure Markdown design reduces deployment risk
  • Cold-start execution model is well-motivated and explicitly documented per step
  • Installation section covers both full ECC and standalone vendored scenarios
  • MIT license present and correctly attributed
  • References upstream project (antbotlab/blueprint) for transparency and derivation context
  • Anti-pattern catalog and adversarial review process mentioned but not fully detailed — would benefit from expanded checklist examples in the skill itself
Model: claude-haiku-4-5-20251001Analyzed: Jul 14, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2

Content updated

2026-07-14

Latest
v1.1

Content updated

2026-04-20

v1.0

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

2026-03-16

Use affaan-m/blueprint in your dev environment

Command Palette

Search for a command to run...