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/forgetgit clone --depth 1 https://github.com/SukinShetty/Nemp-memoryWhat 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 | $0.00005 | $0.01083 |
| Opus 5 | $0.00003 | $0.00541 |
| Sonnet 5 | $0.00001 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
forget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp:forget
Delete a memory by key.
Usage
/nemp:forget /nemp:forget --force # Skip confirmation
Arguments
key: The exact key of the memory to delete
Instructions
When the user invokes /nemp:forget, follow these steps:
1. Find the Memory
Search for the memory in both storage locations:
# Check project memories
[ -f ".nemp/memories.json" ] && cat .nemp/memories.json
# Check global memories
[ -f "$HOME/.nemp/memories.json" ] && cat $HOME/.nemp/memories.json
2. Handle Not Found
If no memory with that key exists: ❌ Memory not found: "" Did you mean one of these?
auth-flow auth-config user-auth-prefs
Use /nemp:list to see all available keys.
3. Confirm Deletion (unless --force)
Show the memory content and ask for confirmation: ⚠️ Delete this memory? Key: Value: "" Agent: <agent_id who wrote it> Created: Source: project/global Type 'yes' to confirm, or 'no' to cancel.
Use the AskUserQuestion tool with options:
- "Yes, delete it"
- "No, keep it"
4. Perform Deletion
If confirmed:
- Read the appropriate memories.json file
- Filter out the memory with the matching key
- Write the updated array back to the file
5. Log the Delete Operation
echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] DELETE key=<key> agent=${CLAUDE_AGENT_NAME:-main}" >> .nemp/access.log
6. Check Auto-Sync Config (REQUIRED)
IMPORTANT: This step is MANDATORY. Always check and execute auto-sync if enabled.
After deleting the memory, read the config file:
[ -f ".nemp/config.json" ] && cat .nemp/config.json
If .nemp/config.json exists and contains "autoSync": true:
6a. Read all remaining memories from .nemp/memories.json
6b. Group memories by category using these rules:
- Keys containing "project", "workspace" → "Project Info"
- Keys containing "stack", "storage", "structure" → "Technical Details"
- Keys containing "feature", "command" → "Features"
- All other keys → "Other"
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.
- 3d ago First seen · 159 lines · 5 tokens per session scan A 7472514c4efd
forget is a command published in the GitHub repository SukinShetty/Nemp-memory (128 stars, last pushed 2mo ago), licensed MIT. It adds 5 tokens to every session and 1,083 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
README
Git workflow and quality assurance commands for the claude-skills repository.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
hunt
Active vulnerability hunt against a target by invoking tools/hunt.py (which calls vulnscanner.sh against recon/ /). Auto-runs recon first if no recon dir exists. Usage: /hunt target.com.
writing:review
Exhaustive parallel editorial review of written content.
everme-help
Print a concise EverMe plugin status + reference card.
recall
Recall relevant EverMe memories from past sessions and use them as context for the current task.