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/auto-capturegit 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/auto-capture)<a href="https://agentmods.dev/commands/sukinshetty/nemp-memory/auto-capture"><img src="https://agentmods.dev/badge/commands/sukinshetty/nemp-memory/auto-capture.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 | $0.00006 | $0.00942 |
| Opus 5 | $0.00003 | $0.00471 |
| Sonnet 5 | $0.00001 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
auto-capture 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nemp-pro:auto-capture
Toggle automatic activity capture on or off.
Usage
/nemp-pro:auto-capture on # Enable auto-capture
/nemp-pro:auto-capture off # Disable auto-capture
/nemp-pro:auto-capture status # Check current status
/nemp-pro:auto-capture # Show status (same as status)
Arguments
on: Enable automatic activity capture for this projectoff: Disable automatic activity capturestatus: Show current auto-capture status (default if no argument)
Instructions
When the user invokes /nemp-pro:auto-capture, follow these steps:
1. Parse Argument
Extract the action: on, off, or status (default to status if empty).
2. Configuration File Location
Auto-capture config is stored in: .nemp-pro/config.json
{
"autoCapture": {
"enabled": true,
"tools": ["Edit", "Write", "Bash"],
"capturePatterns": {
"Edit": "file modifications",
"Write": "new files created",
"Bash": "git commits, npm/bun commands"
}
}
}
3. Handle Actions
For on:
mkdir -p .nemp-pro
Read or create .nemp-pro/config.json, set autoCapture.enabled = true, write back.
Confirm:
Auto-capture ENABLED
What will be captured:
- Edit: File modifications
- Write: New files created
- Bash: Git commits, npm/bun commands
Activities saved to: .nemp-pro/activity.log
Review with: /nemp-pro:activity
For off:
Read .nemp-pro/config.json, set autoCapture.enabled = false, write back.
Confirm:
Auto-capture DISABLED
No automatic activity capture will occur.
For status:
Read .nemp-pro/config.json and display current state:
Auto-capture Status
Enabled: Yes/No
Tools monitored: Edit, Write, Bash
Activity log: .nemp-pro/activity.log
Entries captured: N
Commands:
/nemp-pro:auto-capture on - Enable
/nemp-pro:auto-capture off - Disable
/nemp-pro:activity - View captured activities
4. Initialize Config (if not exists)
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 · 169 lines · 6 tokens per session scan A 389b4f7d94a8
auto-capture is a command published in the GitHub repository SukinShetty/Nemp-memory (128 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 942 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.
convert-to-todowrite-tasklist-prompt
Purpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements.
security-audit
Perform a comprehensive security audit of the codebase to identify potential vulnerabilities, insecure patterns, and security best practice violations.
encode-repo
Bootstrap a repository into Forgetful's knowledge base.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.