syntropic

Ship better software. Prove it on your own code first.

A development methodology for AI-assisted coding. Works with Claude Code, Cursor, Windsurf, GitHub Copilot, and OpenAI Codex.

Try Before You Install

npx syntropic audit

Analyses your last 20 git commits for process issues — localhost references, env files in git, commit discipline, fix ratios, governance docs. No install needed. Nothing sent anywhere. See what the methodology catches on your code.

Install

npx syntropic init

You get: a disciplined development pipeline, governance doc templates, and a connection to the PRISM methodology network — so your rules stay current as the methodology evolves.

What You Get

Evergreen Rules — battle-tested development rules fetched fresh at every cycle:

| Rule | What it prevents | Real-world save | |------|-----------------|-----------------| | EG1: Pre-flight | Localhost refs, broken builds reaching production | Caught 3 localhost references pre-deploy | | EG7: Pipeline | AI jumping to code without research or planning | Structured 210+ features across Full/Lightweight/Minimum cycles | | EG8: Test first | Untested changes reaching production users | Every change verified on test page before promotion | | EG10: Env hygiene | Env var corruption (trailing newlines, wrong formats) | Prevented silent API failures across 6 providers | | EG11: Prod sync | Access control divergence between test and production | Caught lockout bug before 8+ users were affected | | EG14: Doc discipline | Lost decisions, repeated mistakes, no project memory | Backlog, issues, and ADRs updated every cycle |

Governance Docs — project management templates your AI assistant reads before every cycle:

.claude/docs/NORTH_STAR.md     Your vision, goals, and design principles
.claude/docs/BACKLOG.md        Prioritised work with status tracking
.claude/docs/ISSUES.md         Bug log and iteration tracker
.claude/docs/adr/              Architectural Decision Records

Pipeline Agents — research, dev, plan, qa, devops, security — fetched from the PRISM network so they're always up to date.

Health Check — daily GitHub Action with auto-remediation (npm audit fix PRs).

Deep Analysis

syntropic analyse

Run a full venture analysis from your terminal. The CLI reads your codebase (stack, routes, data model, dependencies), sends a product profile to the SyntropicWorks server, and runs the analysis through 8 philosophy lenses:

| Lens | What it evaluates | |------|-------------------| | Outcome Alignment | Is the business structurally coupled to customer success? | | Simplicity | Can anything be removed without loss? | | Growth & Bootstrapping | What's the zero-budget path to 1,000 users? | | Assumption Testing | What's the cheapest way to disprove each key assumption? | | Pricing Architecture | Does the tier structure move buyers from "whether" to "which"? | | Deep Integration | If this disappeared tomorrow, what would break? | | Capability Access | Who's excluded today, and what barriers gatekeep them? | | Legal & Regulatory | What creates liability, and can compliance become a moat? |

How it works:

1. CLI auto-detects your project (package.json, routes, schema, infrastructure)
2. You describe your idea or venture
3. Server runs the full analysis — screening, report generation, 8 lens deep dives, validation plan
4. CLI shows real-time progress as each lens completes
5. Report displays in your terminal and saves to .syntropic/reports/

Everything runs server-side. Your idea text goes up, the finished report comes back. Analysis prompts, agent logic, and orchestration never leave the server.

syntropic analyse --idea "glamping site in the Cotswolds"  # Non-interactive
syntropic analyse --focus "pricing strategy"               # With a specific focus
syntropic analyse --list                                   # Browse past analyses
syntropic analyse --dry-run                                # Preview product profile only

Requires a free account (syntropic login).

Track Record

Built in production on a real product (31 AI agents, 8-lens analyser, CLI, 8 decision tools, 92 API endpoints) over 7 months:

• 210+ features shipped, each through a structured pipeline
• 98% first-try success rate across 42 tracked PRISM cycles
• ~370k tokens saved — ~14k per complex cycle, ~9k lightweight, ~4k minimum
• 0 undetected production incidents after methodology adoption

Trust & Privacy

Everything is local. Your .claude/ directory — rules, agents, governance docs — lives in your repo. It's yours.

Telemetry is metadata only. PRISM learns from anonymous structural metadata about development cycles — never from your code, file contents, or project details.

What's collected: cycle weight, phases run, success/failure, tool used, OS, framework detected, file count bucket (1-5 / 6-20 / 21+), governance doc presence. Never collected: file contents, file names, code, diffs, commit messages, project names, identity, API keys.

Why it matters. Every anonymous report adds signal — which cycle weights work for which project shapes, where pipelines break down, what patterns lead to first-pass success. More contributors = better data = smarter rules for everyone.

Contributors get more. When telemetry is enabled, your PRISM sync fetches live network benchmarks — real success rates, iteration counts, and pattern intelligence computed from aggregate data across all contributors. When disabled, you still get the full EG rules and agents, but benchmarks are static baselines only. No account needed — your identity is a double-hashed device fingerprint (pseudonymisation details).

| | Community (telemetry off) | Contributor (telemetry on) | |---|---|---| | EG rules | Full | Full | | Pipeline agents | Full | Full | | Governance docs | Full | Full | | Benchmarks | Static baselines | Live network data | | Pattern intelligence | Frozen snapshot | Updated from aggregate reports | | Cycle recommendations | Generic defaults | Tuned by real data |

Default: on. Opt out anytime:

syntropic telemetry disable

Clean exit. Remove everything syntropic added (preserves your governance docs):

syntropic remove

Inspect the output. Run npm pack on the package — everything that ships is plain text templates. The methodology is served from a public API endpoint you can curl yourself.

Commands

syntropic audit                    # Analyse git history (no install needed)
syntropic init [project-name]      # Install methodology + docs + post-commit hook
syntropic add cursor windsurf      # Add tools to existing project
syntropic remove                   # Clean uninstall (preserves docs)
syntropic health                   # Run pre-flight checks
syntropic report                   # Submit anonymous cycle report
syntropic autofire status          # Check if post-commit hook is installed
syntropic autofire enable|disable  # Manage the post-commit hook
syntropic telemetry status         # Check telemetry setting
syntropic analyse                  # Deep-dive analysis (requires login)
syntropic analyse --list           # Browse past analyses
syntropic analyse --dry-run        # Preview product profile without sending
syntropic login                    # Sign in (needed for analyse only)
syntropic logout                   # Sign out
syntropic whoami                   # Show current auth status

syntropic init flags

syntropic init --no-hook           # Skip installing the post-commit hook
syntropic init --no-email          # Skip the optional email prompt
syntropic init --yes               # Non-interactive (defaults to all tools, no email prompt)

How It Works

Your instruction file contains a bootstrap rule (EG13) that fetches the full methodology from the PRISM network at cycle start. Rules, agents, and patterns are served fresh — always current, zero maintenance. Your LLM does all compute. Syntropic serves the methodology but runs zero inference.

The governance docs give your AI assistant project memory — it checks priorities before coding and logs issues after. Over time, your docs become a structured record of every decision, bug, and iteration.

Existing Projects

Running syntropic init in a project that already has a CLAUDE.md or .cursorrules appends the methodology — never overwrites. A <!-- syntropic --> marker prevents duplicates.

Research

The methodology is grounded in published research: zenodo.org/records/17894441

Links

• Website
• Intelligent Analyser — deep-dive product analysis through 8 philosophy lenses

License

MIT