Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/superpitt/self-improving-memory-mcp/context-recoverygit clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcpWrote 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.
[](https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/context-recovery)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02572 |
| Opus 5 | $0.00000 | $0.01286 |
| Sonnet 5 | $0.00000 | $0.00514 |
| Haiku 4.5 | $0.00000 | $0.00257 |
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 4d 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.
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:
- Silently search for session-snapshot entities from last 24 hours
- If found with status="in-progress" or "paused": Immediately present recovery option
- If user confirms: Load and apply complete context
- 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:
-
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:"
-
Checkpoint reference
- User mentions: "from previous conversation", "we were working on"
- User pastes formatted continuation summary
-
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
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.
- 4d ago First seen · 431 lines · 0 tokens per session scan A 34acb998e93c
context-recovery is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 11mo 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.
Other agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
starlight-repos-extractor
Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.