clean

clean is a command for coding agents from ramdhavepreetam/NervaPack. It costs 0 tokens per session (827 once invoked), scanned A, original, MIT.

A command that removes NervaPack’s imported graph, vector, and query-history data so a project can start ingestion again. NervaPack is a tool that stores searchable project data.

In plain words
What is it for?
Use it to wipe selected stores or all imported data, preserve memory.db, and prepare for a fresh ingestion.
Why use it?
It clears duplicate, incorrect, stale, or corrupted imported data without deleting the agent’s saved memory.

Command

Install

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.

agentmods
npx agentmods add commands/ramdhavepreetam/nervapack/clean
Clone the repo
git clone --depth 1 https://github.com/ramdhavepreetam/NervaPack

Wrote 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.

agentmods badge for clean

README.md
[![agentmods](https://agentmods.dev/badge/commands/ramdhavepreetam/nervapack/clean.svg)](https://agentmods.dev/commands/ramdhavepreetam/nervapack/clean)
Your own site
<a href="https://agentmods.dev/commands/ramdhavepreetam/nervapack/clean"><img src="https://agentmods.dev/badge/commands/ramdhavepreetam/nervapack/clean.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00827
Opus 5 $0.00000 $0.00413
Sonnet 5 $0.00000 $0.00165
Haiku 4.5 $0.00000 $0.00083

Measured 4d ago against content hash 7d91e7803a46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean 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.

docs/user-guide/commands/clean.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nervapack clean

Remove ingested graph data and start fresh.


Synopsis

nervapack clean [OPTIONS]

Description

clean deletes the files NervaPack writes into .nervapack/ so you can re-ingest from scratch. Use it when:

  • You ran nervapack ingest . multiple times and have duplicate embeddings in ChromaDB
  • You ingested the wrong directory and want to start over
  • The graph or vector store is corrupt or stale
  • You want to reduce disk space used by .nervapack/

clean never touches memory.db (your agent memory store) — decisions, facts, and sessions are always preserved.


Options

Option Description
--vectors Wipe the ChromaDB vector store only (chroma_db/)
--graph Delete graph.graphml only
--history Clear query_history.jsonl and graph_history.jsonl
--all Everything above — full wipe, keeps memory.db
--yes / -y Skip the confirmation prompt (useful in scripts/CI)
--path PATH Project root where .nervapack/ lives (default: .)

Examples

Fix duplicate embeddings after multiple ingests

nervapack clean --vectors
nervapack ingest .

Delete everything and re-ingest from scratch

nervapack clean --all
nervapack ingest .

Non-interactive full wipe (CI / scripting)

nervapack clean --all --yes
nervapack ingest .

Clean a different project's graph

nervapack clean --all --path /path/to/project

What gets deleted

Flag Files removed
--vectors .nervapack/chroma_db/ (the entire ChromaDB directory)
--graph .nervapack/graph.graphml
--history .nervapack/query_history.jsonl, .nervapack/graph_history.jsonl
--all All of the above

Never deleted: .nervapack/memory.db (agent memory — bi-temporal SQLite store).


Output

The following will be permanently deleted:

  What                    Path                        Size
 ──────────────────────────────────────────────────────────
  ChromaDB vector store   ./.nervapack/chroma_db   38.1 MB
  Graph (graph.graphml)   ./.nervapack/graph.graphml 1.4 MB

Note: memory.db (agent memory) is never touched by clean.

Proceed? [y/n]: y
✓ Deleted: ChromaDB vector store
✓ Deleted: Graph (graph.graphml)

Clean complete. Run nervapack ingest . to rebuild.

Read the full file on GitHub · 130 lines

Changes

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.

  1. 4d ago First seen · 130 lines · 0 tokens per session scan A 7d91e7803a46

Subscribe to this mod's changes

clean is a command published in the GitHub repository ramdhavepreetam/NervaPack (1 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 827 tokens. 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 2026-08-31.