parsidion: Instructions file for Claude Code

CLAUDE.md

parsidion CLAUDE.md is an instructions file for Claude Code, Codex from paulrobello/parsidion. It costs 13,928 tokens per session, scanned B, original, MIT.

Repository instructions for Parsidion, a tool that gives coding agents a persistent, searchable knowledge vault containing skills, agents, hooks, and integrations.

In plain words
What is it for?
Use them when modifying the installer, vault skill, agents, hook scripts, search tools, or the Parsidion MCP sub-project.
Why use it?
They clarify the difference between source files and installed files, helping ensure changes are made in the right place and then reinstalled correctly.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: SessionStart hook event, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is paulrobello/parsidion's own configuration. It tells Claude Code and Codex how to work on parsidion 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 parsidion configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/yourname/Repos/myproject.

Reuse

Borrowing it

Nothing to install: this file belongs to paulrobello/parsidion. 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/paulrobello/parsidion/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/paulrobello/parsidion

Made for: Claude Code, Codex.

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 parsidion CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/paulrobello/parsidion/claude-md"><img src="https://agentmods.dev/badge/instructions/paulrobello/parsidion/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,928 This file is loaded in full into every session.
When invoked 13,928 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.13928 $0.13928
Opus 5 $0.06964 $0.06964
Sonnet 5 $0.02786 $0.02786
Haiku 4.5 $0.01393 $0.01393

Measured today against content hash 927a671a1993, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

parsidion CLAUDE.md scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Hook scripts | `skills/parsidion/scripts/` | referenced from `~/.claude/settings.json` |
CLAUDE.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to AI coding assistants when working with code in this repository.

Project Overview

Parsidion is the source repository for an agent-agnostic markdown knowledge vault: skills, agents, hook scripts, search/index tools, and visualizer/MCP integrations that give coding agents persistent memory. Claude Code remains the primary installed adapter today, but the core vault tooling is runtime-agnostic.

Installed vs Source Paths

Component Source (this repo) Installed to
Installer entrypoint install.py run in-place (uv run install.py)
Installer package installer/ (Python package: cli, plan, steps, paths, hooks, skill, schedule, vault, ui, uninstall, colors) imported by install.py
Parsidion vault skill skills/parsidion/ ~/.claude/skills/parsidion/
Agents agents/ (research-agent.md, vault-explorer.md, project-explorer.md, vault-deduplicator.md) ~/.claude/agents/
Hook scripts skills/parsidion/scripts/ referenced from ~/.claude/settings.json
parsidion-mcp sub-project parsidion-mcp/ (own Makefile, pyproject.toml, src, tests) standalone MCP server
Agent extensions extensions/<agent>/ (e.g. extensions/pi/parsidion/) agent-specific integrations
Vault (generated) ~/ParsidionVault/ (legacy ~/ClaudeVault/ fallback; or custom path)

Install model (ARC-026): The skill install differs by platform.

  • macOS / Linuxinstaller/skill.py:install_skill() symlinks ~/.claude/skills/parsidion back to this repo (skills/parsidion/), so edits to source files are live in the installed location without a reinstall. The same applies to the visualizer's vault hooks, which can import vault_common directly from the repo.
  • Windows — symlinks require elevated privileges or a Developer-mode opt-in, so the installer falls back to shutil.copytree. Edits under skills/ are not picked up live; re-run uv run install.py --force --yes after every source change.

Read the full file on GitHub · 498 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. today Changed · +7 lines · +629 tokens per session 927a671a1993
  2. 4d ago Changed · +12 tokens per session 05e490baa529
  3. 5d ago Changed · +2 lines · +144 tokens per session 0742cbe39800
  4. 9d ago First seen · 489 lines · 13,143 tokens per session scan B 901290dfa56c

Subscribe to this mod's changes

parsidion CLAUDE.md is an instructions file published in the GitHub repository paulrobello/parsidion (10 stars, last pushed today), licensed MIT. It adds 13,928 tokens to every session, about $0.0696 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens