agentmods.dev

agentropix-mcp: Instructions file for Claude Code

CLAUDE.md

agentropix-mcp CLAUDE.md is an instructions file for Claude Code from galvangabriel-web/agentropix-mcp. It costs 10,380 tokens per session, scanned A, original, MIT.

A set of instructions for maintaining the Agentropix-SIFT documentation portal, including its file structure, accuracy rules, templates, and diagrams. A documentation portal is a website or repository where project documentation is organized for readers.

In plain words
What is it for?
For editing or adding documentation pages, following the portal’s reading order, checking canonical facts, and creating diagrams that render correctly in GitLab.
Why use it?
It keeps documentation changes consistent with the portal’s source of truth and prevents unsupported or conflicting technical claims.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; built for openclaw.

This is galvangabriel-web/agentropix-mcp's own configuration. It tells Claude Code how to work on agentropix-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentropix-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/admin2/agentropix-sift.

not rated 0repo 2mo ago A scan 10,380 tokens original MIT
View source ↗ galvangabriel-web/agentropix-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to galvangabriel-web/agentropix-mcp. 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/galvangabriel-web/agentropix-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/galvangabriel-web/agentropix-mcp

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.

agentmods badge for agentropix-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/galvangabriel-web/agentropix-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/galvangabriel-web/agentropix-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/galvangabriel-web/agentropix-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/galvangabriel-web/agentropix-mcp/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.

agentmods 80×15 button for agentropix-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/galvangabriel-web/agentropix-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/galvangabriel-web/agentropix-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,380 This file is loaded in full into every session.
When invoked 10,380 The same file — it is already loaded in full.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.10380 $0.10380
Opus 5 $0.05190 $0.05190
Sonnet 5 $0.02076 $0.02076
Haiku 4.5 $0.01038 $0.01038

Measured 8d ago against content hash a6bcecbeb688, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agentropix-mcp CLAUDE.md 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 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.

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.

CLAUDE.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Agentropix-SIFT Documentation Portal

Conventions for working on this documentation portal. Read before editing or adding any page. The portal is the reader-facing docs for Agentropix-SIFT; INDEX.md is the routed master index and README.md is the landing page. Sections live under docs/01-overview … docs/11-ADR, plus docs/12-CASES-REPORTS (sealed DFIR case reports) — 12 numbered categories; each section's reading order is layered on via a "Read in this order" list, non-destructively — filenames are not renamed.

Source of truth & accuracy

  • Canonical numbers come from docs/08-reference/canonical-facts.md — 73 MCP tools, 16 forensic wrappers, 4687 tests, 72/72 (100%) disk recall, 108/118 (91.5%) memory recall, Python 3.12+. Never state a number that contradicts it. Stale figures may only appear inside an explicit "earlier draft said X, canonical is Y" reconciliation note.
  • The main repo /home/admin2/agentropix-sift (docs + src/) is the oracle. Every non-obvious claim, command, flag, path, and tool name must be verifiable there; cite the source file. The oracle wins any conflict with portal prose or imported source material.

MCP-call accuracy (validate every tool/plugin against the live MCP)

Docs are full of 🖥️ MCP calls and run_volatility plugins; a wrong name is a real, demo-breaking bug.

  • Every documented MCP tool name must exist in the live tool list (73 tools — query tools/list via the MCP, or docs/04-mcp-tools/tool-list.md). Non-tools that crept into drafts: get_hashdump/hashdump (no credential-dump capability is exposed — drop the step), get_srum (→ srum_extract), and mmls used as an MCP slot (→ get_partitions/parse_gpt; note fls is a real tool). When unsure, query the live tools/list — don't guess.
  • run_volatility plugins must be a short alias (pslist,malfind,cmdline,netscan,svcscan, pstree,dlllist,…) or a full canonical id (windows.cmdline.CmdLine). The bare middle form windows.cmdline is rejected.
  • No "identify the OS" step on a raw memory image. windows.info/banners are not allowlisted, and get_image_info is EWF/E01-only (returns empty on raw .mem/.raw/.bin). The kernel profile auto-detects on the first windows.* plugin (get_pslist) — a populated pslist confirms the symbol-table match; empty + kernel.symbol_table_name error = no profile resolved (honest negative). get_image_info is correct only for disk/E01 cases.
  • Recurring fixes + the full sweep live in docs/issues/CASE-GUIDE-AUDIT.md.

Read the full file on GitHub · 410 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. 8d ago First seen · 410 lines · 10,380 tokens per session scan A a6bcecbeb688

Subscribe to this mod's changes

agentropix-mcp CLAUDE.md is an instructions file published in the GitHub repository galvangabriel-web/agentropix-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 10,380 tokens to every session, about $0.0519 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 2026-08-31.

Writing and docs
Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens