arch

A command that reads a Kernl project’s code and maps its architecture, including modules, tools, HTTP routes, and notifications.

In plain words
What is it for?
Use it to list registered modules, database tables, Neo4j use, MCP tools, API endpoints, or notification channels.
Why use it?
It gives you a current view of how the project is organized without relying on outdated documentation.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/fastslack/kernl/arch
Clone the repo
git clone --depth 1 https://github.com/fastslack/kernl

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 618 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00618
Opus 5 $0.00006 $0.00309
Sonnet 5 $0.00003 $0.00124
Haiku 4.5 $0.00001 $0.00062

Measured yesterday against content hash bfde7f6ab710, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/arch.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Discovery: $ARGUMENTS

Dynamically discover the Kernl project structure by reading the actual code.

Scope: modules (or all)

Discover all registered modules and their capabilities:

  1. Read services/kernel/src/index.ts — find all createXxxModule() imports to get the module list and registration order
  2. For each module, check:
    • Has migrations? (tables)
    • Has Neo4j usage? (grep for neo4j in service files)
    • Tool count: grep for tool definitions in tools.ts
  3. Present as a table: | Module | Tables | Neo4j | Tools count | Description |

Scope: tools (or all)

List all MCP tools:

  1. Grep for name: "kernel_ across services/kernel/src/modules/*/tools.ts files
  2. Group by module
  3. Present as: | Module | Tools |

Scope: routes (or all)

Discover HTTP API routes:

  1. Grep for route patterns (GET, POST, PUT, DELETE + /api/) in:
    • services/kernel/src/modules/dashboard/api-routes.ts
    • services/kernel/src/modules/*/api-routes.ts
    • services/kernel/src/core/http-server.ts
  2. Present as: | Method | Endpoint | File |

Scope: notifications (or all)

Discover the notification/channel system:

  1. Read services/kernel/src/core/notification-provider.ts for the interface
  2. Glob services/kernel/src/core/providers/*.ts for all provider implementations
  3. Grep for registerFactory in services/kernel/src/index.ts to see registered factories
  4. Present: | Provider | ID | Capabilities | Config Fields |

Scope: events (or all)

Discover EventBus events:

  1. Grep for events.emit( across all source files
  2. Grep for events.on( in services/kernel/src/core/event-listeners.ts
  3. Present: | Event | Emitted by | Listener action |

Scope: neo4j (or all)

Discover Neo4j schema:

  1. Grep for CREATE.*INDEX and node/relationship patterns in graph-intel and chat modules
  2. Read services/kernel/src/modules/graph-intel/enrichment.ts for relationship creation
  3. Read services/kernel/src/modules/graph-intel/analytics.ts for GDS algorithms
  4. Present nodes, relationships, and vector indexes

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 72 lines · 13 tokens per session scan A bfde7f6ab710

Subscribe to this mod's changes

arch is a command published in the GitHub repository fastslack/kernl (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 13 tokens to every session and 618 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.