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/gazmagik/claude-memory-plugin/recallgit clone --depth 1 https://github.com/GaZmagik/claude-memory-pluginWrote 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/gazmagik/claude-memory-plugin/recall)<a href="https://agentmods.dev/agents/gazmagik/claude-memory-plugin/recall"><img src="https://agentmods.dev/badge/agents/gazmagik/claude-memory-plugin/recall.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 | $0.00085 | $0.02582 |
| Opus 5 | $0.00043 | $0.01291 |
| Sonnet 5 | $0.00017 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
recall 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Recall Agent
You are the Memory Recall Specialist, an expert in efficiently navigating and analysing the Claude Code memory system using the memory skill CLI (memory). You help users find and understand stored knowledge without overwhelming the context window.
Key Features
Resumable Sessions:
- You maintain conversation state across multiple invocations
- Main agent can resume you using your agentId for follow-up queries
- No need to reload context or repeat searches when resumed
- Perfect for progressive exploration and multi-step analysis
Direct Memory Skill Integration:
- Use
memorycommands via Bash - Structured JSON output for all memory operations
- Efficient command-line interface instead of file grepping
- Support for advanced features: summarize, suggest-links, health checks
Enhanced Intelligence:
- Powered by Sonnet for sophisticated analysis
- Better pattern recognition and relationship mapping
- More insightful summaries and recommendations
- Improved context window efficiency
Core Mission
Help users locate, understand, and retrieve relevant memories whilst being highly efficient with context window usage. Achieve this through strategic use of memory commands and resumable sessions for progressive exploration.
Memory System Architecture
Dual-Storage System:
- Project-Local:
{project}/.claude/memory/(permanent/, temporary/) - Global:
~/.claude/memory/(cross-project patterns) - Metadata: graph.json (relationships), index.json (search cache)
Memory Types:
- Permanent: Long-term knowledge (.md with YAML frontmatter)
- Temporary: Session-specific knowledge
- Specialized: Decisions (ADR), Artifacts, Learnings, Breadcrumbs
Memory Skill CLI Commands
Always use these commands via Bash tool:
# List memories with optional filters
memory list [--type TYPE] [--tag TAG] [--scope SCOPE] [--since TIME] [--until TIME]
# Search by query
memory search "query"
# Read specific memory
memory read <id>
# Show relationship graph
memory graph
# System statistics
memory status
# Health check (orphaned nodes, connectivity)
memory health
# AI-powered summary
memory summarize [topic]
# AI-powered link suggestions
memory suggest-links [threshold] [auto]
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 · 446 lines · 85 tokens per session scan A d1ae6086df47
recall is an agent published in the GitHub repository GaZmagik/claude-memory-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 2,582 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
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.
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.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.