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/health)<a href="https://agentmods.dev/commands/sukinshetty/nemp-memory/health"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/health.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 | $0.00009 | $0.02021 |
| Opus 5 | $0.00005 | $0.01010 |
| Sonnet 5 | $0.00002 | $0.00404 |
| Haiku 4.5 | $0.00001 | $0.00202 |
Grade A, and why
health 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 7d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp:health
Run a health check on your Nemp Memory system. Detect corruption, stale data, sync drift, orphaned keys, and silent degradation before they cause problems.
Usage
/nemp:health # Run health check with score and issues list
Why This Exists
Every memory tool assumes your data is fine. They silently degrade — ghost references, corrupted indexes, stale CLAUDE.md, orphaned keys. You don't notice until the agent makes a wrong decision based on bad context.
/nemp:health catches problems before they break your agent.
Instructions
When the user invokes /nemp:health, run ALL checks below in sequence, then display a scored report.
Step 1: Check .nemp/ Directory Exists
[ -d ".nemp" ] && echo "NEMP_DIR_EXISTS" || echo "NEMP_DIR_MISSING"
If .nemp/ doesn't exist:
❌ CRITICAL: No .nemp/ directory found.
Run /nemp:init to initialize Nemp Memory.
Stop here — no further checks possible.
Step 2: Check memories.json Exists and Is Valid JSON
[ -f ".nemp/memories.json" ] && python3 -c "import json; data=json.load(open('.nemp/memories.json')); print(f'VALID_JSON entries={len(data)}')" 2>&1 || echo "MISSING_OR_INVALID"
Checks:
- File exists → ✅ or ❌
- Valid JSON → ✅ or ❌ (report parse error line if invalid)
- Entry count → Report number
Step 3: Memory Integrity Checks
For each memory entry in memories.json, verify:
3a. Key format:
- Keys should be kebab-case (lowercase, hyphens)
- Flag keys with spaces, uppercase, or special characters
- Severity: ⚠️ WARNING
3b. Value length:
- Values should be under 200 characters (compressed)
- Flag values over 200 chars
- Severity: ⚠️ WARNING
3c. Empty values:
- Flag any memory where value is empty string, null, or undefined
- Severity: ❌ ERROR
3d. Duplicate keys:
- Check for near-duplicates like "auth-flow" and "auth_flow" or "authflow"
- Severity: ⚠️ WARNING
3e. Timestamp integrity:
createdshould be a valid ISO-8601 dateupdatedshould be >=created- No timestamps in the future
- Severity: ⚠️ WARNING
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.
- 7d ago First seen · 246 lines · 9 tokens per session scan A 0fa1001cf989
health is a command published in the GitHub repository SukinShetty/Nemp-memory (128 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 2,021 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.
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
checkpoint
Save a mid-session checkpoint — for continuity between sessions of the same day.
lessons
Lists the feedback memories captured for the current project (and globally) — the "lessons" learned from user corrections.