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/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/log)<a href="https://agentmods.dev/commands/sukinshetty/nemp-memory/log"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/log/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/commands/sukinshetty/nemp-memory/log"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/log.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 | $0.00011 | $0.00697 |
| Opus 5.5 | $0.00004 | $0.00279 |
| Sonnet 5.5 | $0.00002 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
log 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 16d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp:log
View reads, writes and deletes recorded by participating Nemp command instructions. This log is not a complete record of every filesystem access or manual edit.
Usage
/nemp:log # Show last 20 entries /nemp:log --tail 50 # Show last 50 entries /nemp:log --agent backend # Filter by agent name /nemp:log --clear # Clear the log
Instructions
1. Read Access Log
[ -f ".nemp/access.log" ] && tail -20 .nemp/access.log
If no log exists: 📋 No access log yet. The log tracks automatically when you use: /nemp:save → WRITE entries /nemp:recall → READ entries /nemp:forget → DELETE entries /nemp:init → INIT entries
2. Parse and Display
Default (last 20 entries): 📋 Nemp Access Log TIMESTAMP ACTION KEY AGENT 2026-02-11 14:30:00 INIT (6 memories) nemp-init 2026-02-11 14:32:15 READ auth-flow main 2026-02-11 14:35:00 WRITE api-design backend 2026-02-11 14:35:02 READ auth-flow frontend 2026-02-11 14:35:03 READ database tester 2026-02-11 14:40:00 DELETE old-api main Agents active: main, nemp-init, backend, frontend, tester
With --agent filter:
grep "agent=backend" .nemp/access.log
📋 Access Log — Agent: backend TIMESTAMP ACTION KEY 2026-02-11 14:35:00 WRITE api-design 2026-02-11 14:36:00 READ auth-flow 2 entries by "backend"
With --tail N:
tail -N .nemp/access.log
With --clear: Ask confirmation, then:
rm .nemp/access.log
Log Format
Each line: [ISO-TIMESTAMP] ACTION key=KEY agent=AGENT_NAME extra=INFO
Examples: [2026-02-11T14:30:00Z] WRITE key=auth-flow agent=nemp-init chars=45 [2026-02-11T14:32:15Z] READ key=auth-flow agent=main query=auth [2026-02-11T14:40:00Z] DELETE key=old-api agent=main [2026-02-11T14:30:00Z] INIT agent=nemp-init memories_saved=6
Related Commands
/nemp:list- List all memories/nemp:save- Save a memory (creates WRITE log)/nemp:recall- Recall a memory (creates READ log)
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.
- 16d ago Changed 64194ba2aa2e
- 1mo ago First seen · 80 lines · 11 tokens per session scan A 15865ac48f80
log is a command published in the GitHub repository SukinShetty/Nemp-memory (139 stars, last pushed 14d ago), licensed MIT. It adds 11 tokens to every session and 697 once invoked, about $0.0000 per session on Opus 5.5. 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.
iai-directive
Record, list, or remove a standing order the user typed themselves.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
lessons
Lists the feedback memories captured for the current project (and globally) — the "lessons" learned from user corrections.
setup
Configure mnemonic for proactive memory operations.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).