Index of every page on this site: llms.txt
All skills
qoderai avatar

/architecture-model-bootstrap

@c6240a8
by qoderaiqoderai/better-harness2.5k stars
208
Run it yourself

Use to refine a generated Better Harness architecture model into a confirmed one for the Impact pane. Trigger when a project has no .better-harness/architecture/model.json, when the Impact pane shows an "Auto-generated" model, or when a reader asks to name, merge, split, re-kind, or describe the derived Container/Component structure and propose external systems before saving it as declared.

Use this Skill: https://skilld.dev/gh/qoderai/better-harness/architecture-model-bootstrap

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesmodel-schema.md

≈830 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Model Schema

The exact shape a bootstrapped model must take. This is arch-core's own model — the shape the Impact host consumes and architecture-model.ts validates. Emit it exactly, or the Impact pane reports the model as unreadable.

model.json

A JSON object with two required arrays.

{
  "elements": [
    {
      "id": "studio-server",
      "name": "Studio Server",
      "kind": "Component",
      "description": "Routes, providers and native host supervision.",
      "technology": "Node",
      "tags": ["server"],
      "parent_id": "harness-studio"
    }
  ],
  "relationships": [
    {
      "id": "server-calls-native",
      "source_id": "studio-server",
      "target_id": "native-services",
      "description": "calls staged hosts",
      "technology": null,
      "kind": "DeclaredRelationship"
    }
  ]
}

Element fields

Field Required Rule
id yes Non-empty, unique across all elements. Stable ids keep diffs and bindings meaningful.
name yes Non-empty, human-readable.
kind yes One of Person, SoftwareSystem, Container, Component.
description no One line grounded in what the element's files do. null allowed.
technology no Free text or null.
tags no String array. Keep a generated tag on any element still unconfirmed.
parent_id no The id of the containing element, or null for a root. Must reference a real element.

Relationship fields

Field Required Rule
id yes Non-empty, unique across relationships.
source_id / target_id yes Each must be an existing element id. Never point at an element you did not keep.
kind yes One of Contains, Imports, ResolvedCall, DeclaredHttp, DeclaredRelationship.
description no What crosses the relationship.
technology no Free text or null.

Use the kind that fits the evidence: Imports/ResolvedCall for observed code edges, DeclaredHttp for a declared HTTP dependency, DeclaredRelationship for a hand-declared one, and Contains only where a parent/child is not already expressed by parent_id.

bindings.json

A JSON array mapping path globs to element ids. Every element that should light up when its code changes needs at least one binding; an element with no binding draws but never marks.

[
  { "path_glob": "packages/harness-studio/src/server/**", "element_id": "studio-server" }
]
  • path_glob must match at least one real tracked path in the worktree.
  • element_id must be an id present in model.json.
  • Prefer the narrowest glob that captures the element's sources; overlapping globs bind a path to the first element that matches it.

Validity checklist

Before handing the model back for Save as declared model:

  • elements and relationships are both arrays.
  • Every element has a non-empty id and name, and a valid kind.
  • Every parent_id, source_id, and target_id references an existing element.
  • Every binding element_id exists, and every path_glob matches a real path.
  • No element is kept without at least one binding grounding it in real source.
  • Proposed external systems / people carry their evidence in the description.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill facilitates the creation of software architecture models by analyzing source code, manifests, and documentation. While it processes untrusted documentation files, its behavior is strictly governed by grounding rules that require all model elements to be backed by verifiable code paths, and its output is limited to a structured JSON schema.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at c6240a8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 months ago

README badge

README badge for qoderai/better-harness/architecture-model-bootstrap