Borrowing it
Nothing to install: this file belongs to Athroniaeth/piighost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Athroniaeth/piighost/master/CLAUDE.mdgit clone --depth 1 https://github.com/Athroniaeth/piighostWrote 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/instructions/athroniaeth/piighost/claude-md)<a href="https://agentmods.dev/instructions/athroniaeth/piighost/claude-md"><img src="https://agentmods.dev/badge/instructions/athroniaeth/piighost/claude-md.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 5.1 | $0.02631 | $0.02631 |
| Opus 5 | $0.01316 | $0.01316 |
| Sonnet 5 | $0.00526 | $0.00526 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
piighost 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
PIIGhost is a composable PII de-identification pipeline for LLM agents. It detects, anonymizes, and deanonymizes sensitive entities using pluggable detectors (regex, GLiNER2, spaCy, Transformers, LLM), with a LangChain middleware for LangGraph agents, TOML/JSON-driven configuration, and an HTTP client for the companion piighost-api server. The design is hexagonal: every stage is a port (an Any* runtime_checkable Protocol) with a Base* template ABC, and configuration couples to the core in one direction only.
Development Commands
uv sync # Install dependencies (dev group included)
make format # Auto-fix: ruff format + ruff check --fix
make lint # Blocking gate: ruff format --check + ruff check + pyrefly + bandit
uv run pytest # Run all tests (integration tests deselected by default)
uv run pytest tests/pipeline/test_pipeline.py -k "test_name" # Run a single test
uv run pytest -m integration # Run integration tests (load torch/gliner2/spacy)
make docs-build # Build EN + FR docs (zensical)
make docs-watch # Serve EN docs with live reload (docs-watch-fr for FR)
make lint is a real gate (non-mutating, fails on any issue); use make format to auto-fix. Tests marked integration load heavy optional dependencies and are excluded by the default addopts. asyncio_mode = "auto", so async tests need no decorator.
Architecture
Each pipeline stage is a package under src/piighost/components/ whose base.py holds the port (Any* Protocol) and a Base* template ABC; concrete adapters are sibling modules.
Anonymization Pipeline
AnonymizationPipeline (pipeline/base.py, extends BaseAnonymizationPipeline) runs the stages in order. Only the detector is required: the linker defaults to ExactEntityLinker, the anonymizer to Anonymizer(LabelCounterPlaceholderFactory()), and the overlap resolver to ConfidenceOverlapResolver (the render stage assumes disjoint spans); the expand, entity-resolve, override, and guard stages default to disabled.
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.
- 3d ago Changed · +86 tokens per session 0a92a3f7d754
- 7d ago First seen · 107 lines · 2,545 tokens per session scan A fcb39061d904
piighost CLAUDE.md is an instructions file published in the GitHub repository Athroniaeth/piighost (13 stars, last pushed 3d ago), licensed MIT. It adds 2,631 tokens to every session, about $0.0132 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 instructions, from other repositories
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.
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).
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.
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.
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).
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.