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/export)<a href="https://agentmods.dev/commands/sukinshetty/nemp-memory/export"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/export/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/export"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/export.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 | $0.00007 | $0.02134 |
| Opus 5.5 | $0.00003 | $0.00854 |
| Sonnet 5.5 | $0.00001 | $0.00427 |
| Haiku 4.5 | $0.00001 | $0.00213 |
Grade A, and why
export 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 15d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp:export
Export all project memories to CLAUDE.md. Use --replace to overwrite the entire file, or run without flags to append/update the Nemp section only.
Usage
/nemp:export # Append or update Nemp section in CLAUDE.md
/nemp:export --replace # Replace entire CLAUDE.md with Nemp content only
Arguments
- (no args): Append or update the Nemp section in
CLAUDE.md --replace: Replace the entireCLAUDE.mdinstead of appending/updating
Instructions
When the user invokes /nemp:export, follow these steps:
Step 1: Parse Arguments
Identify which flag (if any) the user provided:
(no args) → Export to CLAUDE.md (append/update)
--replace → Export to CLAUDE.md (full replace)
If the argument is unrecognised, display the Usage block above and stop.
Memory Loading (shared by all export paths)
Before generating any export file, perform these steps to load and prepare memories.
Step 2: Read memories.json
Read .nemp/memories.json:
[ -f ".nemp/memories.json" ] && cat .nemp/memories.json
If the file does not exist, stop and show:
❌ No memories to export.
Save some memories first:
/nemp:save stack Next.js 15 with TypeScript
/nemp:init (auto-detect project stack)
Step 3: Parse Format (with Backward Compatibility)
The file may use either format:
New array format:
{
"memories": [
{
"key": "version",
"value": "0.3.0",
"created": "2026-02-26T16:00:00.000Z",
"updated": "2026-02-26T16:00:00.000Z",
"tags": ["auto-detected"],
"type": "fact",
"vitality": { "state": "active" }
}
]
}
Legacy flat-object format:
{
"stack": { "value": "Next.js", "created": "...", "updated": "..." },
"auth": { "value": "NextAuth", "created": "...", "updated": "..." }
}
If the parsed JSON does not have a memories array, treat each top-level key as a memory entry with:
key = the JSON key name
value = entry.value
created = entry.created
updated = entry.updated
type = entry.type (if present, else undefined)
vitality = entry.vitality (if present, else undefined)
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.
- 15d ago Changed · -6 lines c4d87fc77666
- 1mo ago First seen · 291 lines · 7 tokens per session scan A c9b74d1ad4a8
export is a command published in the GitHub repository SukinShetty/Nemp-memory (139 stars, last pushed 13d ago), licensed MIT. It adds 7 tokens to every session and 2,134 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.
setup
Configure mnemonic for proactive memory operations.
lessons
Lists the feedback memories captured for the current project (and globally) — the "lessons" learned from user corrections.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).