agentleFS
leninejuniorleninejunior/engrene-memory-bridge/.agents/skills/memory-bridge/SKILL.md

memory-bridge

Skill12 starsChanged 56 days agoMITView on GitHub

Local-first memory bridge for AI workflows. Use to read project context and handoff before starting work, record session events and technical decisions during or after tasks, search past memory, and build clean handoffs.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. Ar9av/obsidian-wiki★ 3.7ksame name
    2. wrg32786/aigent-os★ 25same name
    3. chobizzy/llm-wiki★ 3same name
    4. jpoindexter/theft-kit★ 1same name
    5. limsungjoo/codex-claude-memory-bridge★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever working in a project that uses engrene-memory-bridge (indicated by the presence of a .memory-bridge/ folder or when …

    line 10
  2. Distinctive:

    Always inspect the current project state before starting any new task:

    line 30
  3. Distinctive:

    If the project does not have memory initialized yet, initialize it:

    line 37
  4. Distinctive:

    Always rebuild the handoff file so the next AI agent or human teammate starts with up-to-date context:

    line 94

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Memory Bridge Skill

Use this skill whenever working in a project that uses engrene-memory-bridge (indicated by the presence of a .memory-bridge/ folder or when the user asks to track project memory).

memory-bridge ensures continuous context across different AI tools (Antigravity, Claude, Codex, Gemini, Aider, Cursor, Copilot) without vendor lock-in.


Quick Reference Workflow

flowchart LR
    A["Session Start: memory-bridge resume"] --> B["Execute Task"]
    B --> C["Decision Made? memory-bridge decision add"]
    C --> D["Task Done: memory-bridge log"]
    D --> E["Session Wrap-up: memory-bridge handoff build"]

1. At Session Start (Before Starting Tasks)

Always inspect the current project state before starting any new task:

# Get the current objective, pending tasks, recent decisions and warnings:
memory-bridge resume --for antigravity

If the project does not have memory initialized yet, initialize it:

memory-bridge init

You can also read .memory-bridge/handoff.md and .memory-bridge/project-context.md directly.


2. When Making Architectural or Technical Decisions

Whenever a non-trivial choice is made (choosing an engine, altering data format, adding a dependency, refactoring architecture):

memory-bridge decision add \
  --title "Short decision title" \
  --decision "What was decided and chosen" \
  --context "Why this was needed and alternatives considered" \
  --impact "Effects on the codebase and downstream components"

3. After Completing a Task or Significant Action

Record the session event so future sessions and other tools know what happened:

memory-bridge log \
  --tool antigravity \
  --intent "User intent or task description" \
  --summary "Concise summary of actions performed and changes made" \
  --actions "task 1,task 2" \
  --artifacts "file1.ts,file2.md" \
  --tags "feature,ui"

Note: Sensitive secrets (API keys, tokens, private keys) are automatically redacted by the engine.


4. Searching Project Memory

To recall past context, previous sessions, or architectural reasons:

# Hybrid search (combines BM25 keywords + semantic vectors):
memory-bridge search "why did we choose sqlite" --mode hybrid

# Text search:
memory-bridge search "docker compose" --mode text

5. Before Ending the Session or Switching Tools

Always rebuild the handoff file so the next AI agent or human teammate starts with up-to-date context:

memory-bridge handoff build

6. Maintenance & Health Checks

# Check memory file integrity, syntax, and leak risks:
memory-bridge lint

# Deduplicate superseded decisions and clean up handoff:
memory-bridge consolidate

# Inspect overall health:
memory-bridge doctor

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.