syntropic 0.9.6 → 0.9.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +54 -14
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -27,8 +27,8 @@ You get: a disciplined development pipeline, governance doc templates, and a con
27
27
  | Rule | What it prevents | Real-world save |
28
28
  |------|-----------------|-----------------|
29
29
  | **EG1: Pre-flight** | Localhost refs, broken builds reaching production | Caught 3 localhost references pre-deploy |
30
- | **EG7: Pipeline** | AI jumping to code without research or planning | Structured 123 features across Full/Lightweight/Minimum cycles |
31
- | **EG8: Test first** | Untested changes reaching production users | Every fix caught on test page — 12 verified promotions |
30
+ | **EG7: Pipeline** | AI jumping to code without research or planning | Structured 210+ features across Full/Lightweight/Minimum cycles |
31
+ | **EG8: Test first** | Untested changes reaching production users | Every change verified on test page before promotion |
32
32
  | **EG10: Env hygiene** | Env var corruption (trailing newlines, wrong formats) | Prevented silent API failures across 6 providers |
33
33
  | **EG11: Prod sync** | Access control divergence between test and production | Caught lockout bug before 8+ users were affected |
34
34
  | **EG14: Doc discipline** | Lost decisions, repeated mistakes, no project memory | Backlog, issues, and ADRs updated every cycle |
@@ -46,37 +46,74 @@ You get: a disciplined development pipeline, governance doc templates, and a con
46
46
 
47
47
  **Health Check** — daily GitHub Action with auto-remediation (npm audit fix PRs).
48
48
 
49
+ ## Deep Analysis
50
+
51
+ ```bash
52
+ syntropic analyse
53
+ ```
54
+
55
+ 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**:
56
+
57
+ | Lens | What it evaluates |
58
+ |------|-------------------|
59
+ | Outcome Alignment | Is the business structurally coupled to customer success? |
60
+ | Simplicity | Can anything be removed without loss? |
61
+ | Growth & Bootstrapping | What's the zero-budget path to 1,000 users? |
62
+ | Assumption Testing | What's the cheapest way to disprove each key assumption? |
63
+ | Pricing Architecture | Does the tier structure move buyers from "whether" to "which"? |
64
+ | Deep Integration | If this disappeared tomorrow, what would break? |
65
+ | Capability Access | Who's excluded today, and what barriers gatekeep them? |
66
+ | Legal & Regulatory | What creates liability, and can compliance become a moat? |
67
+
68
+ **How it works:**
69
+
70
+ 1. CLI auto-detects your project (package.json, routes, schema, infrastructure)
71
+ 2. You describe your idea or venture
72
+ 3. Server runs the full analysis — screening, report generation, 8 lens deep dives, validation plan
73
+ 4. CLI shows real-time progress as each lens completes
74
+ 5. Report displays in your terminal and saves to `.syntropic/reports/`
75
+
76
+ **Everything runs server-side.** Your idea text goes up, the finished report comes back. Analysis prompts, agent logic, and orchestration never leave the server.
77
+
78
+ ```bash
79
+ syntropic analyse --idea "glamping site in the Cotswolds" # Non-interactive
80
+ syntropic analyse --focus "pricing strategy" # With a specific focus
81
+ syntropic analyse --list # Browse past analyses
82
+ syntropic analyse --dry-run # Preview product profile only
83
+ ```
84
+
85
+ Requires a free account (`syntropic login`).
86
+
49
87
  ## Track Record
50
88
 
51
- Built in production on a real product (27 AI agents, 8-lens analyser, CLI, 7 free tools) over 10 weeks:
89
+ Built in production on a real product (31 AI agents, 8-lens analyser, CLI, 8 decision tools, 92 API endpoints) over 7 months:
52
90
 
53
- - **123 features shipped**, each through a structured pipeline
54
- - **12 test→production promotions** — every feature verified on test page first
55
- - **3 bug classes prevented** by specific EG rules before reaching users
91
+ - **210+ features shipped**, each through a structured pipeline
92
+ - **98% first-try success rate** across 42 tracked PRISM cycles
93
+ - **~370k tokens saved** — ~14k per complex cycle, ~9k lightweight, ~4k minimum
56
94
  - **0 undetected production incidents** after methodology adoption
57
95
 
58
96
  ## Trust & Privacy
59
97
 
60
98
  **Everything is local.** Your `.claude/` directory — rules, agents, governance docs — lives in your repo. It's yours.
61
99
 
62
- **Telemetry is metadata only.** PRISM learns from anonymous structural metadata about development cycles — never from your code, file contents, or project details. This metadata is what drives methodology improvements: which cycle weights work best for which project shapes, where pipelines break down, what patterns lead to first-pass success.
100
+ **Telemetry is metadata only.** PRISM learns from anonymous structural metadata about development cycles — never from your code, file contents, or project details.
63
101
 
64
102
  **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.
65
103
  **Never collected:** file contents, file names, code, diffs, commit messages, project names, identity, API keys.
66
104
 
67
- **Why it matters.** The PRISM network grows exponentially with contributors. 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.
105
+ **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.
68
106
 
69
- **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. This is how the methodology caught 3 classes of production bugs before they reached users, and how 12 test-to-production promotions were verified clean. When telemetry is disabled, you still get the full EG rules and agents, but benchmarks are static baselines only — you lose the network learning that makes rules smarter over time. No account needed — your identity is a double-hashed device fingerprint ([pseudonymisation details](https://zenodo.org/records/17894441)).
107
+ **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](https://zenodo.org/records/17894441)).
70
108
 
71
109
  | | Community (telemetry off) | Contributor (telemetry on) |
72
110
  |---|---|---|
73
111
  | EG rules | Full | Full |
74
112
  | Pipeline agents | Full | Full |
75
113
  | Governance docs | Full | Full |
76
- | Benchmarks | Static baselines | **Live network data** (success rates, iteration counts, failure patterns) |
77
- | Pattern intelligence | Frozen snapshot | **Updated from aggregate reports** (which cycle weights work for your stack) |
78
- | Cycle recommendations | Generic defaults | **Tuned by real data** (upgrade/downgrade triggers from contributor patterns) |
79
- | Network benefit | None | **Your reports improve rules for everyone — including you** |
114
+ | Benchmarks | Static baselines | **Live network data** |
115
+ | Pattern intelligence | Frozen snapshot | **Updated from aggregate reports** |
116
+ | Cycle recommendations | Generic defaults | **Tuned by real data** |
80
117
 
81
118
  Default: on. Opt out anytime:
82
119
 
@@ -103,8 +140,11 @@ syntropic health # Run pre-flight checks
103
140
  syntropic report # Submit anonymous cycle report
104
141
  syntropic telemetry status # Check telemetry setting
105
142
  syntropic analyse # Deep-dive analysis (requires login)
106
- syntropic analyse --list # Browse your past analyses
143
+ syntropic analyse --list # Browse past analyses
144
+ syntropic analyse --dry-run # Preview product profile without sending
107
145
  syntropic login # Sign in (needed for analyse only)
146
+ syntropic logout # Sign out
147
+ syntropic whoami # Show current auth status
108
148
  ```
109
149
 
110
150
  ## How It Works
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "syntropic",
3
- "version": "0.9.6",
3
+ "version": "0.9.7",
4
4
  "description": "Ship better software with a proven development methodology. Audit your git history, install disciplined rules, and track iterations — for Claude Code, Cursor, Windsurf, GitHub Copilot, and OpenAI Codex.",
5
5
  "bin": {
6
6
  "syntropic": "./bin/syntropic.js"