Agent skill

SPARC Methodology

by ruvnet in ruvnet/agentic-flow

Structures complex feature work into five planning-first phases (specification, pseudocode, architecture, refinement and completion) driven through claude-flow commands.

No licenceAuto-check passedDevelopment

Install SPARC Methodology

skills CLI
$ npx skills add ruvnet/agentic-flow --skill sparc-methodology -a claude-code

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

GitHub CLI
$ gh skill install ruvnet/agentic-flow sparc-methodology --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/ruvnet/agentic-flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sparc-methodology .claude/skills/sparc-methodology && 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
sparc-methodology
GitHub stars
816
Used in
6 other repos
Token cost
~6.3k tokens
SKILL.md length
1,166 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
None found

At a glance

Structures complex feature work into five planning-first phases (specification, pseudocode, architecture, refinement and completion) driven through claude-flow commands.

  • Works in 11 steps: Specification → Architecture → Refinement (TDD Implementation) → …
  • Starting a new feature whose requirements are still unclear
  • SKILL.md covers Overview, Table of Contents, Core Philosophy and Development Phases, plus 5 more sections
  • Calls npx

What it does

SPARC puts thorough planning ahead of coding for non-trivial work. The skill defines five phases: specification (requirements, acceptance criteria and constraints), pseudocode, architecture (structure, interfaces and dependencies), refinement based on feedback, and completion with tests and documentation. Each phase starts by routing a task string such as a specification or architecture line through the claude-flow CLI's hooks route command.

A SPARC coordinator agent can be spawned with the same CLI, and two shell scripts support the workflow: sparc-init.sh starts the process for a new feature and sparc-review.sh runs a phase review checklist. It is aimed at new features, architectural changes, system redesigns, integration work and unclear requirements. The skill says to skip it for simple bug fixes, documentation or configuration changes and routine maintenance.

When your agent uses it

  • Starting a new feature whose requirements are still unclear
  • Planning an architectural change or system redesign before writing code
  • Running a phase-by-phase review of a complex integration

Example prompts

  • “Use SPARC to plan a user authentication feature with OAuth2 before we write any code.”
  • “Run the SPARC specification phase for the new billing integration.”
  • “Start the sparc-init script for the notifications feature and take me through pseudocode next.”

Requirements

  • npx access to the @claude-flow/cli package

Workflow steps

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

  1. Specification
  2. Architecture
  3. Refinement (TDD Implementation)
  4. Review
  5. Completion
  6. Memory Integration
  7. Parallel Operations
  8. Hook Integration
  9. Test Coverage
  10. Documentation
  11. File Organization

What it can do on your machine

Read from SKILL.md and the folder at commit e993605. 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

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • npmjs.com

    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

SPARC Methodology loads about 6.3k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 1,166 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~6.3k

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 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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,166 words (~6,250 tokens).

“SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) is a systematic development methodology integrated with Claude Flow's multi-agent orchestration capabilities. It provides 17 specialized modes for comprehensive software development, from initial research through deployment and monitoring.”

— opening of SKILL.md by ruvnet
name
sparc-methodology
version
2.7.0
category
development
tags
sparc, tdd, architecture, orchestration, methodology, multi-agent
author
Claude Flow

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/sparc-methodology of ruvnet/agentic-flow.

Open the folder on GitHubat commit e993605

Used in 10 other repositories

We found 17 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in ruvnet/agentic-flow, which our catalogue first saw on October 7, 2026.

Compare with similar skills

SPARC Methodology 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.

SPARC Methodology compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SPARC Methodology this skillruvnet/agentic-flow8166 repos~6.3kAutomated safety check: PassNone
SPARC Development Methodologyruvnet/ruflo74k2 repos~829Automated safety check: PassMIT
Bulletproof Workflowartemiimillier/bulletproof153—~3.5kAutomated safety check: PassMIT
Think: Plan Before You Buildtw93/Waza7.2k—~3kAutomated safety check: NotesMIT
Architect Before Implementingcursor/plugins10k8 repos~1.4kAutomated safety check: PassNone
PRP PlanWirasm/prp2.3k—~4kAutomated safety check: PassMIT

Similar skills

  • Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    DevelopmentAuto-check passed
  • Bulletproof Workflow

    artemiimillier/bulletproof

    Applies a 12-stage verified workflow, from research to deploy, to non-trivial coding tasks, scaled to lightweight, standard or full mode by task size.

    153 GitHub stars~3.5k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • Turns a rough idea into an approved, decision-complete plan or recommendation before any code is written, for architecture choices and go or no-go calls.

    7.2k GitHub stars~3k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Official

    Sketches types, signatures and module boundaries with stub bodies before real code, compares at least two designs, then implements against the chosen sketch.

    10k GitHub starsUsed in 8 repos~1.4k tokens
    DevelopmentAuto-check passed
  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md…

    40k GitHub starsUsed in 9 repos~420 tokens
    DevelopmentAuto-check passed

More from ruvnet/agentic-flow

All 21 skills in this repo
  • Flow Nexus Neural

    ruvnet/agentic-flow

    Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

    816 GitHub starsUsed in 5 repos~4.1k tokens
    Auto-check passed
  • Stream Chain

    ruvnet/agentic-flow

    Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

    816 GitHub starsUsed in 5 repos~3.2k tokens
    Auto-check passed
  • Agentic Jujutsu

    ruvnet/agentic-flow

    Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

    816 GitHub starsUsed in 4 repos~4.7k tokens
    Auto-check passed
  • Flow Nexus Swarm

    ruvnet/agentic-flow

    Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

    816 GitHub starsUsed in 4 repos~4.2k tokens
    Auto-check passed
  • Hive Mind Advanced

    ruvnet/agentic-flow

    Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

    816 GitHub starsUsed in 4 repos~4.2k tokens
    Auto-check passed
  • Performance Analysis

    ruvnet/agentic-flow

    Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

    816 GitHub starsUsed in 4 repos~3.6k tokens
    Auto-check passed

Works with

Questions about SPARC Methodology

What does SPARC Methodology do?

Structures complex feature work into five planning-first phases (specification, pseudocode, architecture, refinement and completion) driven through claude-flow commands. SPARC puts thorough planning ahead of coding for non-trivial work. The skill defines five phases: specification (requirements, acceptance criteria and constraints), pseudocode, architecture (structure, interfaces and dependencies), refinement based on feedback, and completion with tests and documentation.

When should I use SPARC Methodology?

SPARC Methodology fits situations like: starting a new feature whose requirements are still unclear; planning an architectural change or system redesign before writing code; running a phase-by-phase review of a complex integration.

How do I install SPARC Methodology in Claude Code?

Run `npx skills add ruvnet/agentic-flow --skill sparc-methodology -a claude-code`. Or copy the skill folder (.claude/skills/sparc-methodology in ruvnet/agentic-flow) into .claude/skills/sparc-methodology in your project. Claude Code loads it when a task matches its description.

How do I install SPARC Methodology in Codex?

Run `npx skills add ruvnet/agentic-flow --skill sparc-methodology -a codex`. Or copy the skill folder (.claude/skills/sparc-methodology in ruvnet/agentic-flow) into .agents/skills/sparc-methodology in your project. Codex loads it when a task matches its description.

Can I use SPARC Methodology 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 ruvnet/agentic-flow --skill sparc-methodology -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sparc-methodology, .gemini/skills/sparc-methodology, .github/skills/sparc-methodology and .opencode/skills/sparc-methodology in your project.

What does SPARC Methodology need to run?

Going by SKILL.md and its folder, SPARC Methodology needs the command-line tools its instructions call (npx). Our summary lists: npx access to the @claude-flow/cli package.

Does SPARC Methodology access the network?

SKILL.md names 2 domains. As links in the text: github.com and npmjs.com. This is read from the text; nothing was executed.

Is SPARC Methodology 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 SPARC Methodology use?

No licence was found for SPARC Methodology or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does SPARC Methodology use?

About 6.3k tokens (SKILL.md is roughly 25k 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 SPARC Methodology?

Skills that share tags, products or a category with SPARC Methodology: SPARC Development Methodology (ruvnet/ruflo, 74k stars), Bulletproof Workflow (artemiimillier/bulletproof, 153 stars), Think: Plan Before You Build (tw93/Waza, 7.2k stars) and Architect Before Implementing (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SPARC Methodology?

ruvnet (a GitHub user) maintains it in ruvnet/agentic-flow, which has 816 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 16, 2026.

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