50c 3.9.3 → 3.9.5

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 (8) hide show
  1. package/README.md +201 -175
  2. package/bin/50c.js +2278 -2226
  3. package/lib/backdoor-checker.js +3 -7
  4. package/lib/ip-utils.js +47 -0
  5. package/lib/pre-publish.js +1361 -812
  6. package/lib/team.js +714 -691
  7. package/lib/tools-registry.js +226 -223
  8. package/package.json +1 -1
package/README.md CHANGED
@@ -1,175 +1,201 @@
1
- # 50c
2
-
3
- AI developer tools via MCP. Pay-per-use from $0.01. No subscriptions.
4
-
5
- **Requirements:** Node.js 18+
6
-
7
- ## Quick Start
8
-
9
- ```bash
10
- # Install and configure for your IDE
11
- npx 50c install
12
-
13
- # Set API key (get one at https://50c.ai)
14
- 50c config key YOUR_API_KEY
15
-
16
- # Test it
17
- 50c hints "api design patterns"
18
- ```
19
-
20
- ## MCP Integration
21
-
22
- 50c is an MCP (Model Context Protocol) server. After install, your AI IDE can use all tools directly.
23
-
24
- **Supported IDEs:** Claude Desktop, Cursor, Windsurf, VS Code, Verdent, Cline, Continue, Roo Code
25
-
26
- ### Manual Configuration
27
-
28
- Add to your IDE's MCP config (`~/.cursor/mcp.json`, etc.):
29
-
30
- ```json
31
- {
32
- "mcpServers": {
33
- "50c": {
34
- "command": "npx",
35
- "args": ["-y", "50c@latest"],
36
- "env": {
37
- "FIFTYC_API_KEY": "YOUR_API_KEY"
38
- }
39
- }
40
- }
41
- }
42
- ```
43
-
44
- ## Tools
45
-
46
- ### Free Tools (No API Key Required)
47
-
48
- | Tool | Description |
49
- |------|-------------|
50
- | `web_search` | Internet search |
51
- | `page_fetch` | Fetch and extract URL content |
52
- | `domain_check` | Check domain availability |
53
- | `fm_index`, `fm_find`, `fm_search`, `fm_lines` | Fast file indexing and search |
54
- | `dewey_*` | Knowledge indexing (add, search, list) |
55
- | `fog_check`, `fog_monitor` | Context fog detection |
56
-
57
- ### Paid Tools
58
-
59
- | Tool | Cost | Description |
60
- |------|------|-------------|
61
- | `hints` | $0.05 | 5 brutal 2-word hints |
62
- | `hints_plus` | $0.10 | 10 expanded 4-word hints |
63
- | `roast` | $0.05 | Brutal code review with fixes |
64
- | `genius` | $0.50 | Deep problem solving |
65
- | `genius_plus` | $0.65 | Self-improving code generation |
66
- | `bcalc` | $0.15 | Mathematical discovery engine |
67
- | `bcalc_why` | $0.20 | Deep math explanations |
68
- | `compute` | $0.02 | Python code execution |
69
- | `name_it` | $0.03 | 5 names + domain availability |
70
- | `price_it` | $0.05 | SaaS pricing strategy |
71
- | `one_liner` | $0.02 | 8-word elevator pitch |
72
- | `mind_opener` | $0.08 | 5 curious angles on a problem |
73
- | `prompt_expand` | $0.10 | Expand idea into detailed concept |
74
- | `handoff` | $0.10 | Generate project handoff document |
75
-
76
- ### Context Tools (Beacon)
77
-
78
- | Tool | Cost | Description |
79
- |------|------|-------------|
80
- | `beacon_compress` | $0.02 | Smart context compression |
81
- | `beacon_extract` | $0.01 | Extract decisions/errors/entities |
82
- | `fog_check` | FREE | Check context fog level |
83
- | `fog_monitor` | FREE | Continuous fog monitoring |
84
- | `fog_clear` | $0.03 | Clear fog (compress/extract/reset) |
85
- | `fog_checkpoint` | $0.03 | Save conversation checkpoint |
86
- | `caz_dedup` | $0.02 | Content-addressable deduplication |
87
- | `context_compress` | $0.03 | CAZ + BM25 relevance compression |
88
-
89
- ### Infrastructure Tools
90
-
91
- | Tool | Description |
92
- |------|-------------|
93
- | `cf_list_zones`, `cf_list_dns`, `cf_ssl_status` | Cloudflare management (FREE) |
94
- | `cf_create_dns`, `cf_purge_cache` | Cloudflare write operations ($0.02) |
95
- | `ux_contrast_check`, `ux_spacing_system` | UI/UX utilities (FREE) |
96
- | `ux_color_palette`, `ux_a11y_check`, `ux_roast` | UI/UX analysis ($0.02-$0.05) |
97
-
98
- ## 50c Team
99
-
100
- Natural language orchestration - describe what you want, Team picks the right tools:
101
-
102
- ```
103
- "roast my code and suggest fixes" → roast + hints
104
- "check if coolstartup.ai is available" → domain_check
105
- "research AI trends and summarize" → web_search + genius
106
- ```
107
-
108
- **Enterprise-gated tools** (require `cv_ent_*` API key + 50c-vault):
109
- - `team_ssh` - SSH/SCP/SFTP to servers
110
- - `team_deploy` - Deploy to production
111
- - `team_exec` - Execute remote commands
112
- - `team_http` - HTTP requests to your endpoints
113
-
114
- ## CLI Commands
115
-
116
- ```bash
117
- 50c status # Check connectivity
118
- 50c balance # Check credit balance
119
- 50c config key <key> # Set API key
120
- 50c config show # Show config
121
-
122
- # Direct tool calls
123
- 50c hints "topic"
124
- 50c roast "code snippet"
125
- 50c genius "complex problem"
126
- ```
127
-
128
- ## Companion Packages
129
-
130
- - **50c-vault** - Secure credential storage with passphrase encryption
131
- ```bash
132
- npx 50c-vault init
133
- npx 50c-vault set MY_SECRET
134
- ```
135
-
136
- ## Pricing
137
-
138
- - **Free tier**: 40+ tools (search, file indexing, fog detection, etc.)
139
- - **Pay-per-use**: 1 credit = $0.01, top up anytime
140
- - **No subscriptions**: Credits never expire
141
-
142
- ## Pre-Publish Verification
143
-
144
- Thorough checks before publishing - catch embarrassing mistakes:
145
-
146
- ```bash
147
- # Verify npm package before publish
148
- 50c pre_publish npm
149
-
150
- # Verify arXiv paper
151
- 50c pre_publish arxiv
152
-
153
- # Verify medical/clinical paper
154
- 50c pre_publish medical
155
-
156
- # Other profiles: github, science, math
157
- ```
158
-
159
- **Profiles:**
160
- | Profile | Checks | Use Case |
161
- |---------|--------|----------|
162
- | `npm` | Version bump, links, secrets, syntax, deps | npm publish |
163
- | `github` | Tags, CI, release notes, secrets in history | GitHub release |
164
- | `arxiv` | LaTeX compile, refs, placeholders, code repo | arXiv submission |
165
- | `medical` | IRB, CONSORT, stats, endpoints, disclosures | Clinical papers |
166
- | `science` | Reproducibility, data, claims, figures | Scientific papers |
167
- | `math` | Proofs complete, definitions, notation | Math papers |
168
-
169
- Returns: Score out of 100, pass/fail for each empirical check, manual review items.
170
-
171
- ## Links
172
-
173
- - Website: https://50c.ai
174
- - Docs: https://docs.50c.ai
175
- - Dashboard: https://50c.ai/dashboard.html
1
+ # 50c
2
+
3
+ AI developer tools via MCP. Pay-per-use from $0.01. No subscriptions.
4
+
5
+ **Requirements:** Node.js 18+
6
+
7
+ ## Quick Start
8
+
9
+ ```bash
10
+ # Install and configure for your IDE
11
+ npx 50c install
12
+
13
+ # Set API key (get one at https://50c.ai)
14
+ 50c config key YOUR_API_KEY
15
+
16
+ # Test it
17
+ 50c hints "api design patterns"
18
+ ```
19
+
20
+ ## MCP Integration
21
+
22
+ 50c is an MCP (Model Context Protocol) server. After install, your AI IDE can use all tools directly.
23
+
24
+ **Supported IDEs:** Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Cline, Continue, Roo Code
25
+
26
+ ### Manual Configuration
27
+
28
+ Add to your IDE's MCP config:
29
+
30
+ ```json
31
+ {
32
+ "mcpServers": {
33
+ "50c": {
34
+ "command": "npx",
35
+ "args": ["-y", "50c@latest"],
36
+ "env": {
37
+ "FIFTYC_API_KEY": "YOUR_API_KEY"
38
+ }
39
+ }
40
+ }
41
+ }
42
+ ```
43
+
44
+ ## Security Audit Tool (NEW)
45
+
46
+ Built-in security scanner that checks your machine for backdoors, unauthorized access, and persistence mechanisms. Runs entirely locally. FREE.
47
+
48
+ ```
49
+ backdoor_check
50
+ ```
51
+
52
+ Cross-platform: Windows (17 checks), macOS (22 checks), Linux (13 checks).
53
+
54
+ **What it checks:**
55
+ - RDP/SSH login history with geo-IP tagging of foreign IPs
56
+ - Persistence mechanisms (Registry Run keys, LaunchAgents/Daemons, crontabs, systemd)
57
+ - User accounts and admin group membership
58
+ - Active network connections and listening ports
59
+ - Firewall rules and remote management (WinRM, VNC/ARD)
60
+ - Root certificates and proxy/MITM settings
61
+ - Suspicious IDE artifacts (Verdant, Trae, etc.)
62
+ - SSH authorized_keys anomalies
63
+ - Shell history for suspicious commands
64
+ - macOS: Gatekeeper, SIP, TCC privacy permissions, MDM profiles
65
+
66
+ Returns structured JSON with severity-rated alerts and a verdict (CLEAN / REVIEW / INVESTIGATE).
67
+
68
+ ## Tools Overview
69
+
70
+ ### Free Tools (No API Key Required)
71
+
72
+ | Tool | Description |
73
+ |------|-------------|
74
+ | `web_search` | Internet search with structured results |
75
+ | `page_fetch` | Fetch and extract URL content |
76
+ | `domain_check` | Check domain availability |
77
+ | `contrast_check` | WCAG color contrast checker |
78
+ | `backdoor_check` | Security audit (RDP/SSH, persistence, geo-IP) |
79
+ | `clarity` | Clarity Mode: tools self-activate based on input relevance |
80
+ | `skeptic_pov` | 5-lens adversarial verification |
81
+ | `solve` | Deep iterative solver with self-correction |
82
+ | `fm_index/find/search/lines/summary/list/context` | Fast file indexing and search |
83
+ | `roadmap_add/list/update/delete` | Dev roadmap tracking |
84
+ | `adoption_calc/diagnose/simulate` | Adoption probability modeling |
85
+
86
+ ### Starter Tools ($0.01-$0.05)
87
+
88
+ | Tool | Cost | Description |
89
+ |------|------|-------------|
90
+ | `hints` | $0.05 | 5 brutal 2-word debugging hints |
91
+ | `roast` | $0.05 | Brutal code review with fixes |
92
+ | `name_it` | $0.03 | 5 product names + domain check |
93
+ | `beacon_compress` | $0.02 | Smart context compression |
94
+ | `beacon_extract` | $0.01 | Extract decisions/errors/entities |
95
+ | `fog_check` | $0.05 | Check conversation fog level |
96
+
97
+ ### Pro Tools ($0.08-$0.20)
98
+
99
+ | Tool | Cost | Description |
100
+ |------|------|-------------|
101
+ | `genius` | $0.50 | Deep problem solving |
102
+ | `genius_plus` | $0.65 | Self-improving code generation |
103
+ | `compute` | $0.10 | Execute Python in sandbox |
104
+ | `justice` | $0.10 | Multi-framework ethical reasoning |
105
+ | `artist_mode` | $0.10 | Divergent creative construction |
106
+ | `self_modeling` | $0.08 | Epistemic self-analysis |
107
+ | `seo_audit` | $0.10 | Quick SEO audit |
108
+ | `prompt_fortress` | $0.20 | Prompt security stress-test |
109
+
110
+ ### Titan Deep Solvers (Foundation Tier)
111
+
112
+ Purpose-built multi-phase solvers for hard mathematical and reasoning problems. Each Titan combines multiple 50c tools in orchestrated pipelines with ground-truth verification.
113
+
114
+ | Solver | Cost | Phases | Best For |
115
+ |--------|------|--------|----------|
116
+ | `titan_1` | $10 | 7: Diverge, Ground-truth, Explore, Attack, Resolve, Repair, Verify | Hardest problems. Full adversarial pipeline. |
117
+ | `titan_2` | $5 | 4: Ground-truth, Analysis, Synthesis, Scoring | Math needing compute-anchored verification. |
118
+ | `titan_3` | $10 | 6: Understand, Construct, Verify, Audit, Fix, Synthesize | Proof-heavy problems. |
119
+ | `titan_4` | $2 | 5: Blast, Verify, Fix, Synthesize, Claim Audit | Fast with auto-correction. |
120
+
121
+ **Titan Design Principles:**
122
+ - Compute-before-assert: numerical claims verified by Python before inclusion
123
+ - Ground-truth anchoring: Phase 1 runs brute-force computation to establish facts
124
+ - Claim audit: final phase extracts claims and compares against ground truth
125
+ - Self-correction: auto-corrects when claims don't match computation
126
+
127
+ **Benchmarks (External AGI-2035 Grading):**
128
+ - Titan-2 Q10: B+ - "first submission with appropriate intellectual honesty"
129
+ - Titan-3 Q11: A- at $10/358s - first correct proof across 5 models
130
+
131
+ ### Clarity Mode
132
+
133
+ Intelligent tool auto-selection. Describe your problem and Clarity activates the right tools:
134
+
135
+ ```
136
+ clarity({ input: "Is this proof valid?", mode: "auto", budget_cents: 200 })
137
+ ```
138
+
139
+ ### Skeptic POV
140
+
141
+ Free adversarial verification through 5 lenses: Factual, Logical, Computational, Constructive, STEM.
142
+
143
+ ### Magnum Mathematical Verification Suite
144
+
145
+ | Tool | Cost | Description |
146
+ |------|------|-------------|
147
+ | `magnum_verify_proof` | $0.35 | Proof verification |
148
+ | `magnum_find_error` | $0.30 | Error detection in proofs |
149
+ | `magnum_number_theory` | $0.35 | Number theory specialist |
150
+ | `magnum_test_conjecture` | $0.35 | Adversarial conjecture testing |
151
+ | `magnum_find_theorem` | $0.30 | Find relevant theorems |
152
+ | `magnum_design_computation` | $0.30 | Design computational experiments |
153
+ | `magnum_dependency_dag` | $0.25 | Proof dependency graph |
154
+ | `magnum_symbolic_computational_hybrid` | $0.40 | Hybrid symbolic + computational |
155
+ | `mcp_conductor` | $0.50 | Meta-orchestrator for Magnum suite |
156
+
157
+ ## 50c Team
158
+
159
+ Natural language orchestration - describe what you want, Team picks the right tools:
160
+
161
+ ```
162
+ "roast my code and suggest fixes" -> roast + hints
163
+ "check if coolstartup.ai is available" -> domain_check
164
+ ```
165
+
166
+ ### SSH Server Configuration
167
+
168
+ Configure servers in `~/.50c/servers.json`:
169
+
170
+ ```json
171
+ {
172
+ "prod": { "host": "10.0.0.1", "user": "deploy", "name": "Production" }
173
+ }
174
+ ```
175
+
176
+ ## Pre-Publish Verification
177
+
178
+ ```bash
179
+ 50c pre_publish npm # npm package
180
+ 50c pre_publish arxiv # arXiv paper
181
+ 50c pre_publish medical # Clinical paper
182
+ 50c pre_publish github # GitHub release
183
+ ```
184
+
185
+ ## Pricing Tiers
186
+
187
+ | Tier | Price | Includes |
188
+ |------|-------|----------|
189
+ | Free | $0 | 40+ tools: search, file indexing, security audit, fog detection |
190
+ | Starter | $0.01-$0.05 | Beacon, hints, roast, naming |
191
+ | Pro | $0.08-$0.65 | Genius, compute, SEO, UX, ethics |
192
+ | Enterprise | $0.15-$10 | Titan solvers, Magnum math, CVI |
193
+ | Foundation | Custom | All tools, zero marginal cost |
194
+
195
+ Credits never expire. No subscriptions.
196
+
197
+ ## Links
198
+
199
+ - Website: https://50c.ai
200
+ - Docs: https://docs.50c.ai
201
+ - Dashboard: https://50c.ai/dashboard.html