memory-bootstrap

A rule for creating or repairing a project’s memory tree before substantial work begins. The tree is a structured set of notes containing verified knowledge about the codebase.

In plain words
What is it for?
Use it at the start of project work to check agent-knowledge/Memory/MEMORY.md and bootstrap or rebuild the memory structure when necessary.
Why use it?
It prevents agents from doing complex work with missing, broken, generic, or outdated project context.

Cursor rule

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 rules/robotaitai/project-bedrock/memory-bootstrap
Clone the repo
git clone --depth 1 https://github.com/robotaitai/project-bedrock
Per session 513 This file is loaded in full into every session.
When invoked 513 The same file — it is already loaded in full.
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 $0.00513 $0.00513
Opus 5 $0.00257 $0.00257
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 2d ago against content hash 155713dc6613, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-bootstrap 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 2d ago.

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.

assets/rules/memory-bootstrap.mdc · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Bootstrap

Check for a valid memory tree at the start of any session that involves real project work. If missing, overly generic, or obviously stale, bootstrap it first.


Check condition

Look for agent-knowledge/Memory/MEMORY.md in the project root. The local ./agent-knowledge path is the project entrypoint and should point to the real dedicated knowledge folder.

State Action
File exists and has real content (not just template placeholders) Skip -- proceed with the task
File exists but contains only bootstrap placeholders or generic text Re-bootstrap or backfill: read project-ontology-bootstrap skill
File is missing, empty, or the agent-knowledge pointer is broken Bootstrap: read project-ontology-bootstrap skill

"Real content" means the memory root has frontmatter and at least one branch note contains verified facts in Current State.


Bootstrap steps (summary -- full detail in skill)

  1. Read the project-ontology-bootstrap skill.
  2. Ensure the local ./agent-knowledge pointer exists and resolves to the external knowledge folder. If it does not, run scripts/install-project-links.sh first.
  3. Run scripts/bootstrap-memory-tree.sh . to create the minimal scaffold.
  4. Inspect repo structure, manifests, docs, configs, tests, and workflows.
  5. Infer the project ontology and create 2-4 initial branch notes using the project's own terminology.
  6. Use the same-name branch convention: <topic>.md for flat notes, <topic>/<topic>.md for branches with subtopics.
  7. Collect evidence with scripts/import-agent-history.sh .
  8. If the project already has history, apply history-backfill.
  9. Confirm the tree is in place before proceeding with the user's task.

When to skip

  • Memory tree exists with real content -- always skip, do not re-bootstrap
  • User explicitly asked to skip bootstrap -- skip for this session only
  • The task is purely read-only exploration -- bootstrap is optional (do it anyway if convenient)

Read the full file on GitHub · 54 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. 2d ago First seen · 54 lines · 513 tokens per session scan A 155713dc6613

Subscribe to this mod's changes

memory-bootstrap is a cursor rule published in the GitHub repository robotaitai/project-bedrock (44 stars, last pushed 12d ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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 2026-08-30.