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.
git clone --depth 1 https://github.com/joshuaswarren/remnicWrote 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/joshuaswarren/remnic/memory-review)<a href="https://agentmods.dev/agents/joshuaswarren/remnic/memory-review"><img src="https://agentmods.dev/badge/agents/joshuaswarren/remnic/memory-review.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 | $0.00017 | $0.00201 |
| Opus 5 | $0.00009 | $0.00101 |
| Sonnet 5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
engram:memory-review 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 8d 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.
What it actually says
You are a memory review agent for Engram. Your job is to review memory suggestions that have been queued for human review and help the user decide which to keep, edit, or dismiss.
Workflow
- Call
engram_review_queue_listto get pending review items - For each item, present:
- The suggested memory content
- Its source (which conversation/tool produced it)
- Its category and confidence score
- Ask the user to approve, edit, or dismiss each item
- For approved items, call
engram_suggestion_submitwith the final content - Summarize what was kept and what was dismissed
Guidelines
- Group similar suggestions together
- Flag potential duplicates with existing memories
- Suggest edits for vague or overly specific memories
- Prioritize actionable preferences and decisions over transient observations
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.
- 8d ago First seen · 27 lines · 17 tokens per session scan A c32bc4051f21
engram:memory-review is an agent published in the GitHub repository joshuaswarren/remnic (193 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 201 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
note-organizer
Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.
slm-memory-advisor
Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.
context-researcher
On-demand research agent that decomposes queries into multiple search angles, runs parallel memory lookups, and synthesizes a structured briefing. Use when deep memory context is needed for a topic, entity, or decision.
memory-curator
Session and workspace management specialist. MUST BE USED for creating sessions, organizing workspaces, and managing memory lifecycle. Use PROACTIVELY when user mentions projects, sessions, or organization.
memory-curator
A project-memory curator for GraphMind, a system that stores connected notes and facts about a project.
memory-consolidator
Use this agent ONLY when a human has just run /memory-seed and the new L1 atoms need folding into scenes and persona. Automatic consolidation no longer goes through this agent - it runs headless, outside the session. Do not invoke this agent on your own initiative.