What is NervaPack CLAUDE.md?

A set of Claude Code instructions for NervaPack, a project with tools for searching code and storing agent memory. It requires agents to load project context, query the live codebase, record important findings, and close each session with a summary.

Use it when working on NervaPack to query its code graph, recall or store project memory, and follow the required session and release procedures.

It reduces answers based on stale assumptions and preserves decisions, facts, procedures, and outcomes across coding sessions.

How ramdhavepreetam/NervaPack configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ramdhavepreetam/NervaPack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ramdhavepreetam/NervaPack/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ramdhavepreetam/NervaPack

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ramdhavepreetam/nervapack/claude-md/github.svg)](https://agentmods.dev/instructions/ramdhavepreetam/nervapack/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ramdhavepreetam/nervapack/claude-md"><img src="https://agentmods.dev/badge/instructions/ramdhavepreetam/nervapack/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ramdhavepreetam/nervapack/claude-md"><img src="https://agentmods.dev/badge/instructions/ramdhavepreetam/nervapack/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,376 This file is loaded in full into every session.

When invoked 1,376 The same file — it is already loaded in full.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01376	$0.01376
Opus 5	$0.00688	$0.00688
Sonnet 5	$0.00275	$0.00275
Haiku 4.5	$0.00138	$0.00138

Measured 8d ago against content hash 7f42b3693db8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

NervaPack CLAUDE.md scanned grade B with 2 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo -u preetam`; and `brew audit <path>` is disabled, so audit by name

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -s https://pypi.org/pypi/nervapack/<version>/json` and verify it against

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NervaPack — Claude Code Instructions

Always use NervaPack MCP tools

At the start of every session:

Call memory_start_session("<task name>") to open a named session
Call memory_recall("project context", budget_tokens=400) to load prior decisions and facts
Call query_codebase("<topic>") before answering any question about how the code works

During the session — call memory_store for:

Any decision made (kind="decision" with rationale and alternatives_rejected)
Any fact discovered about system behaviour (kind="fact")
Any procedure or convention established (kind="procedure")
Any outcome from an action (kind="outcome")

At session end:

Call memory_end_session("<one-paragraph summary of what was done>")

Never answer questions about this codebase from training data alone. Always call query_codebase first — it returns AST-precise, token-efficient context from the live graph.

MCP servers available

Server	Command	Purpose
`nervapack`	`nervapack-mcp`	Code graph — `query_codebase`, `graph_status`, `list_entities`
`nervapack-memory`	`nervapack-memory-mcp`	Agent memory — 17 tools for storing and recalling decisions/facts

Project essentials

Version: v0.8.0 (source of truth is version in pyproject.toml)
DB: .nervapack/memory.db (SQLite, auto-resolved from cwd)
Graph: .nervapack/graph.graphml (reingest with nervapack ingest . when source changes)
Tests: python3 -m pytest tests/memory/ -q — must stay green before any commit
Docs: python3 -m mkdocs build --strict — must build clean before any commit
Publish: python3 -m build && python3 -m twine upload dist/nervapack-<version>* Never twine upload dist/* — dist/ keeps every previously built version, and re-uploading one PyPI already has aborts the whole command. Always name the version.
MCP Registry: io.github.ramdhavepreetam/nervapack (published, active)

Read the full file on GitHub · 79 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.

8d ago First seen · 79 lines · 1,376 tokens per session scan B 7f42b3693db8

Subscribe to this mod's changes

NervaPack CLAUDE.md is an instructions file published in the GitHub repository ramdhavepreetam/NervaPack (1 stars, last pushed 15d ago), licensed MIT. It adds 1,376 tokens to every session, about $0.0069 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

NervaPack: Instructions file for Claude Code