context-recovery

Name: context-recovery
Author: jdrhyne

Description

Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do not trigger on a generic "continue" when the current thread already provides an actionable next step.

Usage Guidance

Before installing, understand that this skill may help the agent inspect recent conversation history when context is missing, but it is designed to keep that access bounded, read-only, and approval-based for external sources.

Capability Assessment

✓ Credentials

Conversation and history access are proportionate to the context-recovery purpose, and the skill explicitly forbids broad filesystem searching for session or memory data.

✓ Install Mechanism

The artifact is a single Markdown skill file with no executable scripts, bundled code, dependencies, or install-time behavior.

✓ Instruction Scope

The skill limits activation to explicit recovery needs or evident compaction, prefers current context first, bounds current-thread retrieval, and requires approval for other sources.

✓ Persistence & Privilege

The skill is read-only by default and forbids persisting recovered content unless the user explicitly consents to the exact redacted content and destination.

✓ Purpose & Capability

The stated purpose is recovering missing conversation context, and the instructions are directly focused on bounded, evidence-based recovery.

Version History

v1.3.0

Constrain activation and recovery scope, treat recovered material as untrusted, surface provenance and conflicts, and gate cross-source actions and persistence.

v1.2.2

Scanner hardening: add provenance fields, align _meta version, keep API-only recovery scope and consent-based persistence

v1.2.1

Hardening correction: publish API-first recovery instructions and openclaw metadata (fix previous publish path mismatch)

v1.2.0

Hardening pass: switch to openclaw metadata, remove broad filesystem/shell scan instructions, enforce API-first context recovery and consent-based persistence

v1.1.0

Fix suspicious flag: declare required bins (jq, rg, grep), add Safety Boundaries section documenting file access scope

v1.0.1

Fix: populate summary/description on ClawHub listing

v1.0.0

Initial release: Auto-recover context after session compaction. Adaptive depth fetching, thread-aware recovery, memory caching.

Metadata

Slug context-recovery

Version 1.3.0

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 7

Frequently Asked Questions

What is context-recovery?

Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do not trigger on a generic "continue" when the current thread already provides an actionable next step. It is an AI Agent Skill for Claude Code / OpenClaw, with 6357 downloads so far.

How do I install context-recovery?

Run "/install context-recovery" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is context-recovery free?

Yes, context-recovery is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does context-recovery support?

context-recovery is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created context-recovery?

It is built and maintained by Jonathan Rhyne (@jdrhyne); the current version is v1.3.0.

More Skills

What is context-recovery?

How do I install context-recovery?

Is context-recovery free?

Which platforms does context-recovery support?

Who created context-recovery?

💬 Comments