Agent skill

Blueprinting

by OdradekAI in OdradekAI/bundles-forge

A skill your agent uses when planning new bundle-plugins, splitting complex skills, combining skills into bundles, or exploring a vague idea about packaging skills

Apache-2.0Auto-check passed

Install Blueprinting

skills CLI
$ npx skills add OdradekAI/bundles-forge --skill blueprinting -a claude-code

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

GitHub CLI
$ gh skill install OdradekAI/bundles-forge blueprinting --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/OdradekAI/bundles-forge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/blueprinting .claude/skills/blueprinting && 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
blueprinting
GitHub stars
229
Token cost
~4.4k tokens
SKILL.md length
2,270 words
Files
8 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when planning new bundle-plugins, splitting complex skills, combining skills into bundles, or exploring a vague idea about packaging skills

  • Works in 3 steps: Needs Exploration → Architecture Design → Design Document and Review
  • Planning new bundle-plugins
  • SKILL.md covers Overview, Three Entry Points, Dialogue Strategy and Context Exploration, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Blueprinting is an agent skill from OdradekAI/bundles-forge. Use when planning new bundle-plugins, splitting complex skills, combining skills into bundles, or exploring a vague idea about packaging skills

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/adaptive-mode-questions.md`, `references/advanced-components.md` and `references/composition-analysis.md`).

The repository describes itself as: An agentic skills framework & bundle-plugin engineering toolkit that works. The licence is Apache-2.0.

When your agent uses it

  • Planning new bundle-plugins
  • Splitting complex skills
  • Combining skills into bundles
  • Exploring a vague idea about packaging skills

Example prompts

  • “/blueprinting”

Workflow steps

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

  1. Needs Exploration
  2. Architecture Design
  3. Design Document and Review

What it can do on your machine

Read from SKILL.md and the folder at commit c1b0e10. 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.

    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

Blueprinting loads about 4.4k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 2,270 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.9k

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 OdradekAI/bundles-forge at commit c1b0e10, republished under its Apache-2.0 licence (© OdradekAI). 2,270 words, ~4,377 tokens.

Download SKILL.mdSave it as .claude/skills/blueprinting/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
blueprinting
description
Use when planning new bundle-plugins, splitting complex skills, combining skills into bundles, or exploring a vague idea about packaging skills

Blueprinting Bundle-Plugins

Overview

Turn a vague idea ("I want to package my skills") into a concrete project blueprint through needs exploration, architecture design, and structured review — then orchestrate the full creation pipeline: scaffolding, content authoring, workflow wiring, and initial quality check.

Core principle: Understand what you're building — and why — before generating anything. Five minutes of needs exploration saves hours of rework.

Skill type: Hybrid pattern — follow the three-phase process rigidly, but question selection, depth, and approach recommendations adapt to user context.

Announce at start: "I'm using the blueprinting skill to plan your bundle-plugin."

<HARD-GATE>
Do NOT invoke bundles-forge:scaffolding or any subsequent orchestration phase until the user has approved the design document. Every project — regardless of perceived simplicity — must pass through needs exploration → architecture design → design document review. Quick mode may shorten the process (needs exploration asks only 2 core questions), but it cannot skip it.
</HARD-GATE>
Agent ReasoningReality
"The user's requirements are already clear"Seemingly clear requirements often miss platform, workflow, and visibility architecture decisions
"This is just packaging a few existing skills"Even simple packaging requires compatibility verification, cross-reference validation, and workflow chain mapping
"Moving fast through the process is more efficient"Five minutes of exploration saves hours of rework from missing architecture decisions

Three Entry Points

This skill handles three scenarios. All three feed into the same three-phase interview — only the initial context differs.

  • Scenario A: New project from scratch — Begin with Context Exploration, then the full interview
  • Scenario B: Splitting an existing complex skill — Context Exploration reads the existing skill via references/decomposition-analysis.md, then enters the interview with richer context. Splitting produces a new project. To refactor skills within an existing project, use bundles-forge:optimizing (Skill & Workflow Restructuring target).
  • Scenario C: Composing multiple existing skills — Context Exploration inventories candidates via references/composition-analysis.md, then enters the interview with richer context

If the user has an existing skill they want to break apart, start with Scenario B. If the user has multiple existing skills they want to combine into a new unified project, start with Scenario C. Otherwise, start with Scenario A.

Adding skills to an existing project? That's optimization, not blueprinting. Use bundles-forge:optimizing (Skill & Workflow Restructuring target).

Dialogue Strategy

Read references/dialogue-strategies.md for the full interview protocol. Core principles: ask 1-2 questions at a time, reject vague answers, propose approaches with trade-offs, challenge over-scoping, surface contradictions immediately, and confirm understanding after each phase.

Context Exploration

Before asking any questions, gather available context:

Scenario A (New Project)
  1. Scan the workspace — look for scattered skill files, existing SKILL.md drafts, or relevant project files that hint at what the user is building
  2. If user context is already rich from their initial message, proceed directly to Phase 1
Scenario B (Decomposition)
  1. Read the existing skill — follow references/decomposition-analysis.md to map responsibilities, identify split points, and propose a decomposition
  2. Present the decomposition proposal to the user for approval
  3. Proceed to Phase 1 with the decomposition as input context. In Phase 1, skip questions already answered by the decomposition analysis. Confirm those answers with the user rather than re-asking.
Scenario C (Composition)
  1. Inventory candidate skills — follow references/composition-analysis.md to check compatibility, detect conflicts, and design orchestration
  2. Present the composition plan to the user for approval
  3. Proceed to Phase 1 with the composition analysis as input context. In Phase 1, skip questions already answered by the composition analysis. Confirm those answers with the user rather than re-asking.

Phase 1: Needs Exploration

Understand what the user wants to build and why, before making any architecture decisions. Ask these one at a time, adapting based on answers.

1. Problem Scenario

Ask: "What problem does this skill bundle solve? How are people solving it today?"

Understand the gap between the current state and what the user envisions. This is the foundation for all subsequent decisions.

2. Target Users

Ask: "Who will use this skill bundle? What's their background — what type of developers, what workflows, what platforms?"

The answer shapes platform selection, skill complexity, and documentation style.

3. Core Capabilities

Ask: "What capabilities must this skill bundle provide? If you had to remove one, which one would make it pointless?"

This identifies the non-negotiable skills vs nice-to-haves. The agent should actively propose a skill decomposition based on the answer — present 2-3 decomposition approaches with trade-offs when the boundaries aren't obvious.

4. Usage Flow

Ask: "Walk me through how someone would use this — from installing the plugin to completing their task."

This reveals workflow dependencies, entry points, and the natural sequence of operations.

5. Existing Alternatives (if relevant)

Ask: "Are there similar skill bundles or tools out there? What's different about yours?"

Skip this if the user has already addressed it or if the domain is clearly novel.

Phase 1 Checkpoint

After collecting needs exploration answers, restate the understanding and verify completeness:

"Let me confirm what I understand: You're building [one-sentence summary] for [target users] to solve [problem]. The core capabilities are [list]. The usage flow is [summary]. Does this match your intent?"

Must verify before proceeding:

  • Problem scenario: expressible as "[user] needs to [action] because [reason]" in one sentence
  • Target users: at least one concrete persona with platform + workflow identified

Wait for user confirmation before proceeding to Phase 2. If the user corrects anything, update the understanding and re-confirm.

Phase 2: Architecture Design

With a clear understanding of what and why, now decide how to build it. The agent should actively recommend answers based on Phase 1 context, rather than asking open-ended questions.

Before making architecture recommendations: Explicitly list key assumptions derived from Phase 1 and wait for user confirmation. Template:

"Based on our needs exploration, I'm operating on these assumptions:

  1. [Complexity assumption — e.g., 'This is a straightforward packaging project']
  2. [Platform assumption — e.g., 'Primary platform is Claude Code based on your workflow']
  3. [Independence assumption — e.g., 'Skills appear independent with no workflow chain']

If any of these are wrong, correct me now — they will shape all architecture decisions."

1. Project Complexity

Based on Phase 1 answers, recommend quick or adaptive mode:

Quick mode (quick packaging):

  • Target: bundle standalone skills into a plugin with minimal infrastructure
  • Skip questions 5 (Workflow Chain), 6 (Bootstrap Strategy), and 4a (Skill Visibility)
  • Defaults: no bootstrap, no hooks, Claude Code only
  • Jump to a simplified design document after question 4

Adaptive mode (adaptive deep interview):

  • Full interview with dynamic follow-ups based on answers
  • After core questions, conditionally ask about advanced components

Present the recommendation with reasoning: "Based on what you've described — [reasoning] — I recommend [quick/adaptive] mode. [Quick explanation of what this means]."

Quick mode skips most Phase 1/2 questions and defaults to Claude Code only with independent skills. See references/dialogue-strategies.md for the full behavior summary table.

2. Project Name

Kebab-case identifier (e.g., my-dev-tools). This becomes the directory name, package name, and plugin ID across all platforms.

Validation: lowercase letters, numbers, hyphens only. No underscores, no spaces.

3. Target Platforms

Which platforms should the project support? See references/platform-reference.md for the full platform table and selection strategies.

Based on the target users identified in Phase 1, recommend a platform combination with reasoning. Start with what the user actually uses — others can be added later via bundles-forge:scaffolding.

4. Skill Inventory

Based on the core capabilities and usage flow from Phase 1, propose a skill decomposition rather than asking the user to list skills:

"Based on the capabilities you described, I recommend splitting into these skills: [proposed list with one-sentence purpose each]. Here's why this decomposition makes sense: [reasoning]."

When the decomposition isn't obvious, present 2-3 approaches:

  • Approach A: [decomposition] — pros/cons
  • Approach B: [decomposition] — pros/cons
  • Recommended: [which and why]

For each skill, determine:

  • Skill name (kebab-case)
  • One-sentence purpose
  • Rigid or flexible type

If the user isn't sure yet, scaffold with a single placeholder skill and the bootstrap.

4a–7. Adaptive Mode Questions

Questions 4a (Skill Visibility), 5 (Workflow Chain), 6 (Bootstrap Strategy), and 7 (Advanced Components) apply only in adaptive mode. Quick mode skips them. See references/adaptive-mode-questions.md for the full question set.

Show full SKILL.md (953 more words)Show less
Phase 2 Checkpoint

Restate the architecture decisions and verify completeness before generating the design document.

Must satisfy (missing any one blocks document generation):

  • Core skills: each has a name + one-sentence purpose + type (rigid/flexible)
  • Architecture mode: quick or adaptive, with explicit reasoning documented
  • Target platform: at least one selected, with rationale tied to target users

Should satisfy (mark unmet items as [TBD] in the design document):

  • Workflow chain: dependency graph is drawn (or explicitly marked "all independent")
  • Bootstrap strategy: yes/no decision with reasoning (or "deferred" with rationale)
  • Success criteria: at least one measurable outcome the user can verify post-creation

Wait for user confirmation before proceeding to Phase 3.

Phase 3: Design Document and Review

Generate Design Document

After the interview, compile a design summary using the template in references/design-document-template.md. This template includes both needs context (project overview, target users, use cases, success criteria) and technical architecture (mode, platforms, skills, workflow, components). Conditional fields: fill Third-Party Sources only when Scenario C involves external skills; fill Notes for special constraints not captured elsewhere. Leave unused conditional fields out of the document.

Design Document Self-Review

Before presenting to the user, review the document:

  1. Placeholder scan — any TBD, TODO, or incomplete [TBD] markers? Fix what can be resolved from interview context
  2. Internal consistency — does the skill inventory match the workflow chain?
  3. Scope check — is this focused on a single project? Does it need decomposition into sub-projects first?
  4. Ambiguity check — could any requirement be interpreted two ways? If so, pick one and make it explicit

Fix issues inline. Then present the document to the user.

User Review Gate

Present the design document and ask the user to review:

"Here's the design document. Please review and let me know if anything needs adjustment before I proceed with the creation pipeline."

If the user requests changes, update the document and re-run the self-review. Only proceed to the Orchestration Pipeline when the user explicitly approves.

The user may request going back to a specific phase to re-discuss decisions — support this without restarting from scratch.

Orchestration Pipeline

After the user approves the design, orchestrate the full project creation pipeline. Execute each phase in order — do not skip or reorder phases.

Scaffold

"Design approved. Invoking scaffolding to generate the project structure."

Invoke bundles-forge:scaffolding with the approved design. Wait for scaffolding to complete (including its inspector self-check) before proceeding.

→ verify: inspector self-check passes with 0 critical findings → on fail: fix structural issues inline, re-run inspector before proceeding

Author Content

"Structure generated. Invoking authoring to write skill and agent content."

Invoke bundles-forge:authoring with the full skill inventory from the design document. Pass the complete design document (including project overview, target users, and use cases) so authoring can write more targeted descriptions and overviews. Authoring handles:

  • All SKILL.md files listed in the design
  • All agent definitions (agents/*.md) if the design specifies subagents

Pass the complete list in one invocation — authoring processes them in sequence.

→ verify: every skill in the design has a SKILL.md with valid frontmatter (name, description) → on fail: re-invoke authoring for missing or invalid skills

Wire Workflow

"Content authored. Designing workflow integration."

This step runs within blueprinting — workflow wiring requires the full project context from the interview.

  1. For each skill pair with a dependency in the Workflow Chain, write the ## Integration section:
    • **Calls:** and **Called by:** declarations must be symmetric (A calls B ⟹ B is called by A)
    • Artifact IDs in ## Outputs must match downstream ## Inputs
  2. Update the bootstrap skill's routing table to reflect all entry-point and internal skills
  3. If the design specifies agent dispatch, add dispatch instructions to the orchestrating skill and Dispatched by: to the agent file

→ verify: all Calls/Called-by pairs are symmetric; bootstrap routes match skill inventory → on fail: fix asymmetric links or missing routes before proceeding

Run Audit

"Workflow wired. Running initial audit."

Invoke bundles-forge:auditing on the project root for a baseline quality check.

→ verify: 0 critical audit findings → on warn: present to user, proceed if user approves → on critical: must address before project is considered ready

Common Mistakes

MistakeFix
Skipping needs exploration, jumping to architecture design (see HARD-GATE above)Understand "what and for whom" before deciding "how to build"
Proposing approaches without trade-off analysisEach approach needs pros, cons, best-fit scenario, and an explicit recommendation — not just a list of options
Forgetting workflow chain mappingChains determine bootstrap skill content — an unmapped chain produces a bootstrap that routes incorrectly
Dumping skills into one folder without analyzing compatibilityAudit each skill first — naming conflicts and overlapping responsibilities cause confusion
Copying third-party skills without security auditAlways invoke bundles-forge:auditing on imported content
Treating all third-party skills as repackage-onlyAsk integration intent — workflow integration requires adaptation
Forgetting skill visibility classificationEntry-point vs internal determines description style
Using blueprinting to add skills to an existing projectBlueprinting creates new projects; use bundles-forge:optimizing (Skill & Workflow Restructuring target) for existing ones

Inputs

  • user-requirements (required) — conversational input gathered through the structured interview process
  • existing-skill (optional) — path to existing SKILL.md for Scenario B (decomposition)
  • candidate-skills (optional) — list of existing skills for Scenario C (composition)

Outputs

  • design-document — structured design summary containing project overview, target users, use cases, success criteria, project name, platforms, skill inventory, workflow chain, bootstrap strategy, and advanced components. Contains skill-inventory (consumed by bundles-forge:authoring) and workflow-chain (consumed during the Wire Workflow step). Consumed by bundles-forge:scaffolding and bundles-forge:authoring

Integration

Calls:

  • bundles-forge:scaffolding — Scaffold step: generate project structure and platform adapters
    • Artifact: design-document → design-document (direct match)
  • bundles-forge:authoring — Author Content step: write SKILL.md and agents/*.md content
    • Artifact: design-document → skill-inventory (indirect — skill inventory extracted from design document)
  • bundles-forge:auditing — Run Audit step: initial quality check on the new project
    • Artifact: design-document → project-directory (indirect — auditing targets the scaffolded project, not the design document)

Pairs with:

  • bundles-forge:optimizing — complementary scope: blueprinting for new projects, optimizing for existing ones

© OdradekAI, 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 7 other files (references) in skills/blueprinting of OdradekAI/bundles-forge.

  • SKILL.md
  • references/adaptive-mode-questions.md
  • references/advanced-components.md
  • references/composition-analysis.md
  • references/decomposition-analysis.md
  • references/design-document-template.md
  • references/dialogue-strategies.md
  • references/platform-reference.md

Open the folder on GitHubat commit c1b0e10

Compare with similar skills

Blueprinting 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.

Blueprinting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blueprinting this skillOdradekAI/bundles-forge229—~4.4kAutomated safety check: PassApache-2.0
Blueprintaffaan-m/ECC276k2 repos~604Automated safety check: PassMIT
Blueprintaffaan-m/ECC276k—~421Automated safety check: PassMIT
Blueprintsickn33/agentic-awesome-skills47k2 repos~1kAutomated safety check: PassMIT
Blueprint Construction Planneraffaan-m/ECC276k5 repos~1.3kAutomated safety check: PassMIT
Code Splittingthedaviddias/Front-End-Checklist74k—~492Automated safety check: PassMIT

Similar skills

  • Blueprint

    affaan-m/ECC

    将单行目标转化为多会话、多代理工程项目的分步构建计划。每个步骤包含独立的上下文简介,以便新代理能直接执行。包括对抗性审查门、依赖图、并行步骤检测、反模式目录和计划突变协议。触发条件:当用户请求复杂多PR任务的计划、蓝图或路线图,或描述需要多个会话的工作时。不触发条件:任务可在单个PR或少于3个工具调用中完成,或用户说“直接执行”时。

    276k GitHub starsUsed in 2 repos~604 tokens
    DevelopmentAuto-check passed
  • Blueprint

    affaan-m/ECC

    1行の目的を複数セッション、複数エージェントエンジニアリングプロジェクト向けのステップバイステップ構築計画に変換します。各ステップには自己完結型コンテキストブリーフがあり、新しいエージェントがそれをコールドで実行できます。

    276k GitHub stars~421 tokensUpdated 4 days ago
    DatabasesAuto-check passed
  • Blueprint

    sickn33/agentic-awesome-skills

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

    47k GitHub starsUsed in 2 repos~1k tokens
    Auto-check passed
  • Turns a one-line objective into a multi-step plan file with PR-sized steps, context briefs, a dependency graph, parallel-step detection and an adversarial review.

    276k GitHub starsUsed in 5 repos~1.3k tokens
    Agent WorkflowsAuto-check passed
  • Code Splitting

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing large SPA bundles, new dependency additions, or routes that feel slow to hydrate.

    74k GitHub stars~492 tokensUpdated 2 days ago
    Auto-check passed
  • Triage Support Bundle

    netdata/netdata

    Investigate a Netdata support bundle offline - the archive netdata-support-bundle produces - to explain one host's alerts, missing data, collector failures, crashes, high CPU or memory, streaming…

    81k GitHub stars~2.7k tokensUpdated today
    DevOps & CloudAuto-check passed

More from OdradekAI/bundles-forge

All 8 skills in this repo
  • Releasing

    OdradekAI/bundles-forge

    A skill your agent uses when releasing a bundle-plugin, bumping versions, fixing version drift across manifests, setting up version sync infrastructure, updating CHANGELOG, publishing to…

    229 GitHub stars~3.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Auditing

    OdradekAI/bundles-forge

    A skill your agent uses when reviewing a bundle-plugin for structural issues, version drift, skill quality, workflow integration, or security risks — before releasing, after changes, or after adding…

    229 GitHub stars~5.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Testing

    OdradekAI/bundles-forge

    A skill your agent uses when testing a bundle-plugin locally before release — generating dev-marketplace environments, verifying component discovery, running hook smoke tests, and validating…

    229 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Using Bundles Forge

    OdradekAI/bundles-forge

    A skill your agent uses when starting any conversation involving bundle-plugins — blueprinting, scaffolding, authoring, auditing, testing, optimizing, or releasing.

    229 GitHub stars~1.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Optimizing

    OdradekAI/bundles-forge

    A skill your agent uses when optimizing a bundle-plugin or single skill — improving descriptions, reducing tokens, fixing audit findings, restructuring workflows, adding skills to fill gaps, or…

    229 GitHub stars~5.2k tokensUpdated 5 mo ago
    Auto-check passed
  • Scaffolding

    OdradekAI/bundles-forge

    A skill your agent uses when generating project structure for new bundle-plugins, adding or removing platform support (Claude Code, Cursor, Codex, OpenCode, Gemini CLI, OpenClaw), updating platform…

    229 GitHub stars~3.1k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Blueprinting

What does Blueprinting do?

A skill your agent uses when planning new bundle-plugins, splitting complex skills, combining skills into bundles, or exploring a vague idea about packaging skills. Blueprinting is an agent skill from OdradekAI/bundles-forge.

When should I use Blueprinting?

Blueprinting fits situations like: planning new bundle-plugins; splitting complex skills; combining skills into bundles; exploring a vague idea about packaging skills.

How do I install Blueprinting in Claude Code?

Run `npx skills add OdradekAI/bundles-forge --skill blueprinting -a claude-code`. Or copy the skill folder (skills/blueprinting in OdradekAI/bundles-forge) into .claude/skills/blueprinting in your project. Claude Code loads it when a task matches its description.

How do I install Blueprinting in Codex?

Run `npx skills add OdradekAI/bundles-forge --skill blueprinting -a codex`. Or copy the skill folder (skills/blueprinting in OdradekAI/bundles-forge) into .agents/skills/blueprinting in your project. Codex loads it when a task matches its description.

Can I use Blueprinting 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 OdradekAI/bundles-forge --skill blueprinting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blueprinting, .gemini/skills/blueprinting, .github/skills/blueprinting and .opencode/skills/blueprinting in your project.

What does Blueprinting need to run?

SKILL.md names no scripts, command-line tools or credentials: Blueprinting is instructions for the agent only.

Does Blueprinting 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 Blueprinting 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 Blueprinting use?

Blueprinting 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 Blueprinting use?

About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.

What are the alternatives to Blueprinting?

Skills that share tags, products or a category with Blueprinting: Blueprint (affaan-m/ECC, 276k stars), Blueprint (affaan-m/ECC, 276k stars), Blueprint (sickn33/agentic-awesome-skills, 47k stars) and Blueprint Construction Planner (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blueprinting?

OdradekAI (a GitHub organization) maintains it in OdradekAI/bundles-forge, which has 229 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 27, 2026.

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