agentleFS
Sign inStart free
GabrieleDattileGabrieleDattile/agent-superpowers/skills/memory/memory-nexus/SKILL.md

memory-nexus

Skill1 starsChanged 15 days agoMITView on GitHub

Cross-session architectural memory ledger. Preserves technical decisions, conventions, and context across distinct agent sessions to eliminate repetitive questions and context loss.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    TRIGGER ON QUERY: When the user asks: "why did we build X this way?", "what conventions are we following?", or "what decisions have we …

    line 15
  2. Distinctive:

    When exploring a subsystem:

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

🧠 Skill: Memory Nexus (Cross-Session Context Ledger)

1. When to Trigger (Routing)

  • TRIGGER AT SESSION START: At the start of any new session, query Memory Nexus to reload past architectural decisions and conventions.
  • TRIGGER AT DECISION TIME: Whenever an architectural choice, library selection, or structural trade-off is finalized with the user.
  • TRIGGER ON QUERY: When the user asks: "why did we build X this way?", "what conventions are we following?", or "what decisions have we made?".

2. Fundamental Philosophy

"Coding assistants suffer from session amnesia: closing the terminal wipes all context. Memory Nexus maintains a local, tamper-proof architectural ledger that persists across days, weeks, and agent restarts."

3. Operational Protocol

Phase 1: Ingest Past Context

At the beginning of a conversation, read the ledger:

python skills/memory/memory-nexus/scripts/nexus.py read

The agent absorbs all past architectural agreements (e.g. database choice, naming conventions, authentication strategy).

Phase 2: Record New Decisions

Whenever a non-trivial architectural or technical choice is confirmed:

python skills/memory/memory-nexus/scripts/nexus.py record --decision "Use SQLite with WAL mode" --rationale "Simplicity for single-node deployment without extra daemon"

Phase 3: Query Specific Context

When exploring a subsystem:

python skills/memory/memory-nexus/scripts/nexus.py query --topic "auth"

4. Guardrails & Negative Constraints

  • ❌ NEVER silently overwrite past recorded decisions without explicit user approval.
  • ❌ NEVER store sensitive API secrets or private credentials in the memory ledger.

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.

Check your setup, free