agentleFS
Sign inStart free
limsungjoolimsungjoo/codex-claude-memory-bridge/skills/memory-bridge/SKILL.md

memory-bridge

Skill0 starsChanged 3 months agoMITView on GitHub

Inspect, test, and troubleshoot the local Codex and Claude Code durable-memory bridge without exposing turn bodies.

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. leninejunior/engrene-memory-bridge★ 12same name
    4. chobizzy/llm-wiki★ 3same name
    5. jpoindexter/theft-kit★ 1same 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.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the scripts in this plugin to inspect and troubleshoot local delivery.

    line 8
  2. Very specific:

    Run scripts/codex-turn-notify.py --status from the plugin root.

    line 12
  3. Distinctive:

    Do not print JSON bodies, Markdown memory contents, or log files during routine checks.

    line 15
  4. Distinctive:

    Never inject synthetic records into a live inbox.

    line 22
  5. Distinctive:

    Read a failed JSON body only when the user explicitly authorizes inspection of that private turn.

    line 28
  6. Very specific:

    Keep SHARED_MEMORY_SYNC_ACTIVE=1 around nested LLM calls to prevent recursion.

    line 36

“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

Use the scripts in this plugin to inspect and troubleshoot local delivery.

Check status

Run scripts/codex-turn-notify.py --status from the plugin root.

Report queue counts and paths only. Do not print JSON bodies, Markdown memory contents, or log files during routine checks.

Test safely

Run python3 tests/test_consumer.py.

The tests use temporary roots and a deterministic LLM stub. Never inject synthetic records into a live inbox.

Diagnose failures

Inspect only .reason sidecars under failed/codex-turns and failed/claude-turns first. Reason codes are safe to summarize. Read a failed JSON body only when the user explicitly authorizes inspection of that private turn.

Preserve boundaries

  • Producers must remain deterministic and must not call an LLM.
  • Redaction must happen before any LLM invocation.
  • Runtime directories must remain private and outside the plugin repository.
  • A successful memory and index write must precede moving a record to processed.
  • Keep SHARED_MEMORY_SYNC_ACTIVE=1 around nested LLM calls to prevent recursion.

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