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 commands/sukinshetty/nemp-memory/suggestgit clone --depth 1 https://github.com/SukinShetty/Nemp-memoryWrote 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/commands/sukinshetty/nemp-memory/suggest)<a href="https://agentmods.dev/commands/sukinshetty/nemp-memory/suggest"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/suggest.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 | $0.00007 | $0.10717 |
| Opus 5 | $0.00003 | $0.05359 |
| Sonnet 5 | $0.00001 | $0.02143 |
| Haiku 4.5 | $0.00001 | $0.01072 |
Grade A, and why
suggest 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 — 1,360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp:suggest
Intelligently suggest memories to save based on your recent work patterns.
Usage
/nemp:suggest # Analyze and show suggestions interactively
/nemp:suggest --auto # Automatically save all suggestions
Instructions
You are an intelligent pattern analyzer. Examine the user's recent activity and suggest valuable memories to save.
Step 1: Read Activity Log
Read the activity log from .nemp/activity.log or .nemp-pro/activity.log.
If no activity log exists:
No Activity Log Found
Enable activity capture to get personalized suggestions:
/nemp:auto-capture on
Or manually add memories:
/nemp:save <key> <value>
/nemp:init # Auto-detect project stack
Step 2: Parse and Analyze Patterns
Analyze the activity log entries to identify patterns:
Pattern Detection Categories:
| Category | Detection Method | Suggestion Type |
|---|---|---|
| Hot Files | Files edited 3+ times | important-files |
| Core Modules | Directories with most activity | project-structure |
| Workflow Commands | Repeated bash commands (git, npm, test) | dev-workflow |
| Stack Signals | File extensions + paths | stack-hints |
| Testing Patterns | Test commands + test file edits | testing-workflow |
| Build Patterns | Build/deploy commands | build-workflow |
| New Dependencies | npm/yarn/pnpm install commands | new-packages |
Analysis Rules:
FOR EACH activity entry:
- Track file paths → count modifications per file
- Track directories → identify hot zones (e.g., src/auth/, src/api/)
- Track commands → identify workflow patterns
- Track file types → detect stack usage
- Track install commands → detect new dependencies (Rule 2)
THRESHOLDS:
- File modified 3+ times → IMPORTANT FILE
- Directory has 5+ file edits → CORE MODULE
- Command run 3+ times → WORKFLOW PATTERN
- Same file type in multiple edits → STACK SIGNAL
- Any npm/yarn/pnpm/bun install → NEW DEPENDENCY (always suggest)
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 · 1,360 lines · 7 tokens per session scan A 7ccda51ffe91
suggest is a command published in the GitHub repository SukinShetty/Nemp-memory (128 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 10,717 once invoked, about $0.0000 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 commands, from other repositories
memory-gc
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.
remember
Log current finding or successful pattern to hunt memory. Auto-fills from /validate output if available. Usage: /remember.
encode-repo
Bootstrap a repository into Forgetful's knowledge base.
memory-list
List recent memories from Forgetful.
memory-search
Search memories semantically using Forgetful.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.