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 skills add HelloRuru/claude-memory-engine --skill skillgit clone --depth 1 https://github.com/HelloRuru/claude-memory-engineWrote 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/skills/helloruru/claude-memory-engine/skill)<a href="https://agentmods.dev/skills/helloruru/claude-memory-engine/skill"><img src="https://agentmods.dev/badge/skills/helloruru/claude-memory-engine/skill/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.
<a href="https://agentmods.dev/skills/helloruru/claude-memory-engine/skill"><img src="https://agentmods.dev/badge/skills/helloruru/claude-memory-engine/skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01891 |
| Opus 5.5 | $0.00022 | $0.00756 |
| Sonnet 5.5 | $0.00011 | $0.00378 |
| Haiku 4.5 | $0.00006 | $0.00189 |
Grade B, and why
memory-engine scanned grade B with 1 finding 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 1mo 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
You don't need to remember to run any command before closing. How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Engine v1.6
A memory and learning system for Claude Code, built with hooks and markdown.
Modules
1. Smart Context
Auto-detects the current project from your working directory and loads its memory.
- Resolves per-project memory directory automatically — no hardcoded paths
- Implementation:
~/.claude/scripts/hooks/session-start.js - Config:
references/smart-context.md
2. Auto Learn (Pitfall Detection)
Detects pitfall patterns before context compression — retries, errors followed by fixes, user corrections.
- Saves both the problem and the fix to
~/.claude/skills/learned/ - Same mistake 3+ times across different days → suggests writing it into permanent rules
- Implementation:
shared-utils.js→detectPitfalls()+savePitfalls()
3. Student Loop (/reflect)
8-step learning cycle. First 3 steps are automatic (every session). Last 5 via /reflect.
- Takes notes — records what was done, files changed, decisions made
- Links them — tags the project, connects to previous notes
- Spots patterns — scans for pitfall signals
There is no real "end" to a Claude Code conversation. Memory Engine saves at three points:
- Every 20 messages (
mid-session-checkpoint) — most reliable, self-counted - Before context compression (
pre-compact) — pitfall detection runs here, context is fullest - When conversation ends (
session-end) — best-effort, not guaranteed to fire
You don't need to remember to run any command before closing. 4. Review — read past 7 days, mark useful vs outdated 5. Refine — 4-question decision tree (Keep? Condense? Already covered? Delete as last resort) 6. Re-study — re-analyze cleaned data for buried patterns 7. Slim down — list removable items, wait for user confirmation 8. Wrap up — produce a report
4. Session Handoff (/handoff)
Pass context between Claude Code windows without losing progress.
/handoffsaves ahandoff-*.mdfile with progress, decisions, unfinished tasks- Next session auto-detects it on startup (
session-start.js) - Mid-conversation detection via
memory-sync.js - Each handoff is shown once, tracked by
.handoff-read.json
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 172 lines · 55 tokens per session scan B 60c81523347b
memory-engine is a skill published in the GitHub repository HelloRuru/claude-memory-engine (134 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,891 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
adr-ops
Author, index, and lint Architecture Decision Records — append-only memory that recovers the WHY behind a system's shape. Triggers on: adr, architecture decision record, decision log, record this decision, supersede an adr, why was this decided, adr template, next adr number.
hive-mind-advanced
Queen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use when orchestrating a large swarm of agents under a lead coordinator, building consensus across agents, or maintaining durable cross-agent memory.
creator-productivity
Task management and workspace memory for creative work sessions. Manages a TASKS.md file for project tracking, a two-tier memory system (CREATOR.md + creator-memory/), and a daily sprint structure. Use when organizing creative projects, tracking content tasks, or starting a focused work session.
memory-prune
Manual reviewable prune of stale memory entries. Lists project entries older than 30 days with content preview; Frank decides per-entry [keep | archive | pin]. Keeps MEMORY.md under the auto-load 200-line truncation. Use when MEMORY.md exceeds 180 lines or session-end after a heavy work week.