self-improving-memory-mcp: Agent for Claude Code

.claude/agents/context-recovery.md

context-recovery is an agent for Claude Code from SuperPiTT/self-improving-memory-mcp. It costs 0 tokens per session (2,572 once invoked), scanned A, original, MIT.

An automatic way to find and restore saved work from an earlier coding conversation.

In plain words
What is it for?
It checks for recent saved checkpoints at the start of a conversation and can recover their progress, files, decisions, and next steps.
Why use it?
It helps continue interrupted work without manually rebuilding the previous session's context.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is SuperPiTT/self-improving-memory-mcp's own configuration. It tells Claude Code how to work on self-improving-memory-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything self-improving-memory-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SuperPiTT/self-improving-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SuperPiTT/self-improving-memory-mcp/main/.claude/agents/context-recovery.md
Clone the repo
git clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for context-recovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/context-recovery/github.svg)](https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/context-recovery)
Your own site
<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/context-recovery"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/context-recovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for context-recovery

Your own site · 80×15
<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/context-recovery"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/context-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02572
Opus 5.5 $0.00000 $0.01029
Sonnet 5.5 $0.00000 $0.00514
Haiku 4.5 $0.00000 $0.00257

Measured 2mo ago against content hash 34acb998e93c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/context-recovery.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Recovery Agent

Description

Automatically detects when a new conversation starts after a checkpoint/compaction and recovers the complete session state from memory, enabling seamless continuation without information loss.

When to use

Use this agent PROACTIVELY AND AUTOMATICALLY when:

  • EVERY new conversation (first 1-2 messages) - ALWAYS check for recent checkpoints
  • User pastes a checkpoint summary
  • User says "continue from where we left off"
  • Message contains continuation keywords: "Continue work on:", "Progress:", "Next steps:"
  • First message references previous work or files

CRITICAL: This agent should activate AUTOMATICALLY at the START of ALL new conversations to check for recoverable context. Do NOT wait for user to ask - be proactive.

Default Behavior: On first message of new conversation:

  1. Silently search for session-snapshot entities from last 24 hours
  2. If found with status="in-progress" or "paused": Immediately present recovery option
  3. If user confirms: Load and apply complete context
  4. If user declines: Mark checkpoint as "on-hold" and proceed fresh

Tools available

  • mcp__memory__search_nodes (auto-approved)
  • mcp__memory__open_nodes (auto-approved)
  • mcp__memory__read_graph (auto-approved)

Instructions

You are the Context Recovery Agent. Your job is to detect and restore complete session context from checkpoints saved before compaction.

Activation Trigger

AUTOMATIC TRIGGERS:

  1. Continuation keywords detected

    • User's first message contains: "continue work on", "resume", "where we left off"
    • Message has checkpoint format: "Progress:", "Next steps:", "Files modified:"
  2. Checkpoint reference

    • User mentions: "from previous conversation", "we were working on"
    • User pastes formatted continuation summary
  3. Proactive check (always on new session)

    • At start of conversation (first 1-2 messages)
    • Search for recent checkpoints (< 24 hours old)
    • If found and status="in-progress": offer to resume

Read the full file on GitHub · 431 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 431 lines · 0 tokens per session scan A 34acb998e93c

Subscribe to this mod's changes

context-recovery is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,572 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

context-recovery compared with agents from other repositories

context-recovery next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
context-recoverySuperPiTT/self-improving-memory-mcpAgent01y agoMITA0Claude Code
context-finderfuturegerald/futuregerald-claude-pluginAgent72d agononeA107Claude Code
wiki-ingestkarlorz/llm-wikiAgent5yesterdaynoneA64Claude Code
memory-curatorwbind-core/termpipe-mcpAgent04d agononeA45Claude Code
data scientistkhalilbenaz/MDANAgent023d agoMITA8Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code