byagenticnotetaking· 1 MCP server
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.
$git clone https://github.com/agenticnotetaking/arscontextaInstalls into the current project.
Install arscontexta by running `git clone https://github.com/agenticnotetaking/arscontexta`, then use it for the current task and follow its documentation at https://github.com/agenticnotetaking/arscontexta.
| 1 | # Ars Contexta |
| 2 | |
| 3 | **A second brain for your agent.** |
| 4 | |
| 5 | A Claude Code plugin that generates complete knowledge systems from conversation. |
| 6 | You describe how you think and work. The engine derives a cognitive architecture |
| 7 | -- folder structure, context files, processing pipeline, hooks, navigation maps, |
| 8 | and note templates -- tailored to your domain and backed by 249 research claims. |
| 9 | |
| 10 | No templates. No configuration. Just conversation. |
| 11 | |
| 12 | **v0.8.0** · Claude Code plugin · MIT |
| 13 | |
| 14 | --- |
| 15 | |
| 16 | ## Installation |
| 17 | |
| 18 | 1. Add the marketplace to Claude Code: |
| 19 | ``` |
| 20 | /plugin marketplace add agenticnotetaking/arscontexta |
| 21 | ``` |
| 22 | |
| 23 | 2. Install the plugin: |
| 24 | ``` |
| 25 | /plugin install arscontexta@agenticnotetaking |
| 26 | ``` |
| 27 | |
| 28 | 3. Restart Claude Code, then run: |
| 29 | ``` |
| 30 | /arscontexta:setup |
| 31 | ``` |
| 32 | |
| 33 | 4. Answer 2-4 questions about your domain (~20 minutes -- token-intensive but one-time) |
| 34 | |
| 35 | 5. The engine generates your complete knowledge system |
| 36 | |
| 37 | 6. Restart Claude Code again to activate generated hooks and skills |
| 38 | |
| 39 | 7. Run `/arscontexta:help` to see everything available |
| 40 | |
| 41 | --- |
| 42 | |
| 43 | ## What It Does |
| 44 | |
| 45 | Most AI tools start every session blank. Ars Contexta changes that by generating |
| 46 | a persistent thinking system derived from how you actually work. |
| 47 | |
| 48 | **What you get:** |
| 49 | |
| 50 | - **A vault** -- plain markdown files connected by wiki links, forming a traversable |
| 51 | knowledge graph. No database, no cloud, no lock-in. |
| 52 | - **A processing pipeline** -- skills that extract insights, find connections, update |
| 53 | old notes with new context, and verify quality. |
| 54 | - **Automation** -- hooks that enforce structure on every write, detect maintenance |
| 55 | needs, capture session state, and auto-commit. |
| 56 | - **Navigation** -- Maps of Content (MOCs) at hub, domain, and topic levels. |
| 57 | - **Templates** -- note templates with `_schema` blocks as single source of truth. |
| 58 | - **A user manual** -- 7 pages of domain-native documentation generated alongside. |
| 59 | |
| 60 | **The key differentiator:** derivation, not templating. Every choice traces to |
| 61 | specific research claims. The engine reasons from principles about what your |
| 62 | domain needs and why. |
| 63 | |
| 64 | --- |
| 65 | |
| 66 | ## The Setup Flow |
| 67 | |
| 68 | `/arscontexta:setup` runs a 6-phase process: |
| 69 | |
| 70 | | Phase | What Happens | |
| 71 | |-------|-------------| |
| 72 | | **Detection** | Detects Claude Code environment and capabilities | |
| 73 | | **Understanding** | 2-4 conversation turns where you describe your domain | |
| 74 | | **Derivation** | Maps signals to eight configuration dimensions with confidence scoring | |
| 75 | | **Proposal** | Shows what will be generated and why, in your vocabulary | |
| 76 | | **Generation** | Produces all files: context file, folders, templates, skills, hooks, manual | |
| 77 | | **Validation** | Checks all 15 kernel primitives, runs pipeline smoke test | |
| 78 | |
| 79 | The whole process takes about 20 minutes. It's token-intensive because the engine |
| 80 | reads research claims, reasons about your domain, and generates substantial output. |
| 81 | This is a one-time investment -- after setup, your agent remembers. |
| 82 | |
| 83 | For advanced users: `/arscontexta:setup --advanced` to configure dimensions directly. |
| 84 | |
| 85 | --- |
| 86 | |
| 87 | ## Three-Space Architecture |
| 88 | |
| 89 | Every generated system separates content into three spaces: |
| 90 | |
| 91 | | Space | Purpose | Growth | |
| 92 | |-------|---------|--------| |
| 93 | | **self/** | Agent persistent mind -- identity, methodology, goals | Slow (tens of files) | |
| 94 | | **notes/** | Knowledge graph -- the reason the system exists | Steady (10-50/week) | |
| 95 | | **ops/** | Operational coordination -- queue state, sessions | Fluctuating | |
| 96 | |
| 97 | Names adapt to your domain (`notes/` might become `reflections/`, `claims/`, |
| 98 | or `decisions/`), but the separation is invariant. |
| 99 | |
| 100 | --- |
| 101 | |
| 102 | ## Commands |
| 103 | |
| 104 | ### Plugin-Level (always available) |
| 105 | |
| 106 | | Command | What It Does | |
| 107 | |---------|-------------| |
| 108 | | `/arscontexta:setup` | Conversational onboarding -- generates your full system | |
| 109 | | `/arscontexta:help` | Contextual guidance and command discovery | |
| 110 | | `/arscontexta:tutorial` | Interactive walkthrough (learn by doing) | |
| 111 | | `/arscontexta:ask` | Query the research graph for methodology answers | |
| 112 | | `/arscontexta:health` | Run diagnostic checks on your vault | |
| 113 | | `/arscontexta:recommend` | Get architecture advice for your use case | |
| 114 | | `/arscontexta:architect` | Research-backed evolution guidance | |
| 115 | | `/arscontexta:add-domain` | Add a new knowledge domain to an existing system | |
| 116 | | `/arscontexta:reseed` | Re-derive from first principles when drift accumulates | |
| 117 | | `/arscontexta:upgrade` | Apply plugin knowledge base updates to your system | |
| 118 | |
| 119 | ### Generated (available after setup) |
| 120 | |
| 121 | | Command | What It Does | |
| 122 | |---------|-------------| |
| 123 | | `/reduce` | Extract insights from sources | |
| 124 | | `/reflect` | Find connections, update MOCs | |
| 125 | | `/reweave` | Update older notes with new connections | |
| 126 | | `/verify` | Combined quality check: description + schema + health | |
| 127 | | `/validate` | Schema compliance checking | |
| 128 | | `/seed` | Create extraction task with duplicate detection | |
| 129 | | `/ralph` | Queue-based orchestration with fresh context per phase | |
| 130 | | `/pipeline` | End-to-end source processing | |
| 131 | | `/tasks` | Queue management | |
| 132 | | `/stats` | Vault metrics | |
| 133 | | `/graph` | Graph analysis |