project-ontology-bootstrap

Project Ontology Bootstrap

Creates a minimal knowledge scaffold, then the agent infers the ontology from the real project. Run this once -- then maintain with the writeback rule.

When to use

• agent-knowledge/Memory/MEMORY.md does not exist or is empty
• Memory/MEMORY.md exists but is still generic bootstrap content
• User says "initialize memory", "bootstrap memory", or "set up project memory"
• Starting work on an inherited repo with no prior agent memory

---

Step 0 -- Verify the local pointer

The project entrypoint is ./agent-knowledge.

• ./agent-knowledge must be a symlink or junction to the real dedicated knowledge folder
• The external folder is the source of truth
• Manual and scripted bootstrap still write through ./agent-knowledge as the local handle

If the pointer does not exist yet, create it first with:

scripts/install-project-links.sh --slug <project-slug> --repo /path/to/project

---

Step 1 -- Run the bootstrap script

scripts/bootstrap-memory-tree.sh /path/to/project

This creates a minimal scaffold:

agent-knowledge/
  Memory/
    MEMORY.md           <- root durable memory note
    decisions/
      decisions.md      <- decision log (same-name convention)
  Evidence/
    raw/
    imports/
  Sessions/
  Outputs/
  Dashboards/
  Templates/
  .obsidian/
  STATUS.md

The script detects a profile hint (web-app, robotics, ml-platform, or hybrid) and stores it in STATUS.md. The hint does NOT create branch notes -- that is the agent's job.

---

Step 2 -- Inspect the repo and infer the ontology

After the scaffold exists, inspect:

• Manifests and lockfiles
• Directory structure
• Docs (README.md, AGENTS.md, CLAUDE.md, docs/)
• Config files
• Test directories
• Workflow files
• Any evidence already present under Evidence/

From these signals, determine the project's natural decomposition. Use the project's own terminology, not generic template names.

---

Step 3 -- Create initial branch notes