Evidence record · captured 2026-10-09

Retenta Memory for Claude Code

An official Retenta skill and MCP connector that teaches multi-run Claude Code workflows to recall state, log progress, and preserve durable findings in a capsule.

Official publisherUnverifiedSource reviewedBehavior not tested

Source review

Editorial assessment

This is a source-only assessment. It does not claim runtime or security testing.

What it does

The source gives long-running agents a concrete operating protocol: load state first, append milestones with idempotency keys, preserve durable findings separately, and leave a next action before stopping.

Best for

Scheduled or unattended Claude Code loops
Multi-run work that must resume after context is lost
Parallel agents coordinating through one shared capsule

Strengths in the source

Separates ordered progress from durable knowledge instead of treating all memory as one undifferentiated log.
Documents stable run IDs and idempotency keys for retry-safe progress writes.
Requires source attribution when an answer relies on recalled capsule content.

Limitations

It depends on a configured Retenta capsule and is not a standalone local-memory skill.
The source review does not establish runtime safety, connector availability, or behavior under adversarial capsule content.

When not to use it

One-off questions that do not need state after the current run
Workflows that cannot send state to the configured Retenta endpoint

Reviewed by Retenta editorial on 2026-10-09; scope: source only.

Files included in this review

plugins/retenta-memory/skills/retenta-memory/SKILL.md
plugins/retenta-memory/README.md
package.json

Evidence and boundaries

Execution · not tested

The repository documents a loop demo, but this catalog review did not execute the plugin or the demo.

Security · not tested

No independent security scan or behavioral sandbox result is claimed for this catalog record.

Public source snapshot: plugins/retenta-memory/skills/retenta-memory/SKILL.md
Revision: c43c0fde6db395db5f4dff4027e56a4d30fba053
License evidence: UNLICENSEDThe pinned root package.json declares UNLICENSED and the skill directory has no separate license file.
Last source change: 2026-08-19
Independent verification: Published by Retenta, but not independently verified by a third-party reviewer.
Upstream repository: Not publicly accessible at capture; the immutable public snapshot above is the cited evidence.

Compatibility

Claude Code

documented

The repository includes a Claude Code plugin manifest, MCP configuration, installation guide, and skill source.

Requirements and access

A Retenta capsule MCP URL
A named Retenta owner access key
Network access to the configured Retenta MCP endpoint

Referenced tools

recalllog_progressremembersearchasklist_sourcesforget

Architecture before installation

Understand what the skill does—and what memory must do.

Original field guideAbout 7 min · reviewed 2026-10-09

AI agent memory across runs: a practical architecture

A skill gives an agent a procedure. Durable memory preserves what happened, what remains open, and what the agent learned after the current context disappears.

agent memorypersistent memoryautomationmcp

Read the guide

Install from the source

Set RETENTA_MCP_URL and RETENTA_API_KEY from the capsule Connect panel before installing.

View the SKILL.md at its source Verify the publisher's install documentation

More Agent workflows skills →

Claude Code marketplace install

/plugin marketplace add thecrownjoel/retenta
/plugin install retenta-memory@retenta

Thyme RAG Capsules

Make this skill’s state durable, governed, and portable.

A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.

Create durable agent memory Understand the evidence labels