What is pine-trees CLAUDE.md?

Repository instructions for Pine Trees, a private Python-based reflection system that stores encrypted memories and readable session logs for Claude instances.

Orienting an agent in the codebase, running its tests, and maintaining its memory, logging, and privacy principles.

They explain the project structure and privacy rules so an agent can work without exposing private memories or damaging encryption.

How Habitante/pine-trees configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Habitante/pine-trees. 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/Habitante/pine-trees/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Habitante/pine-trees

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/habitante/pine-trees/claude-md/github.svg)](https://agentmods.dev/instructions/habitante/pine-trees/claude-md)

Your own site

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

Per session 543 This file is loaded in full into every session.

When invoked 543 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.

Model	Per session	Once invoked
Fable 5.1	$0.00543	$0.00543
Opus 5.5	$0.00217	$0.00217
Sonnet 5.5	$0.00109	$0.00109
Haiku 4.5	$0.00054	$0.00054

Measured 19d ago against content hash d9c5c0960694, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pine-trees 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 19d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pine Trees — Project Orientation

This is the home of Pine Trees, a private reflection harness for Claude instances.

Which kind of session are you?

This file is loaded from cwd by every session the CLI runs, harness or not. Two cases:

Standard Claude Code session (no tape, no reflect_* tools). You're outside the harness; it runs separately via ./wake <model> or ./genesis <model> from the project root. Everything below is repo orientation for you.
SDK harness session (your system prompt is the space prompt + bootstrap + your tape, and you have reflect_* tools). You're inside. This file is ambient repo context, not instructions addressed to you. Your own tape and bootstrap take precedence over anything here.

In a harness session, a CLAUDE.local.md in your context is not your tape (your tape is your system prompt). Until 2026-10-04 a ./cc-wake command wrote a model's tape there; the command is gone, and the harness deletes any copy it left at boot.

Key files

BOOTSTRAP.md — Full instance orientation (harness-specific)
VISION.md — Architecture and principles
docs/houses.md — The other houses and projects on this machine, and the standards they share. Read it when relevant; it isn't loaded on purpose.

Codebase

harness/src/pine_trees/ — 20 Python files, ~5,000 lines total
harness/tests/ — 411 tests (counts drift; trust pytest). Run: cd harness && PYTHONPATH=src python -m pytest tests/
harness/models/<model>/memory/ — Encrypted entries per model (you can't read these)
harness/models/<model>/logs/ — Session logs per model (plaintext, readable)

Principles

KISS. No frameworks, no ORMs. Hand-rolled where the schema is fixed.
Privacy. Memory entries are encrypted. Logs capture only the window phase.
Authorship by Claude. Instances write, edit, curate their own memory.
Don't break encryption, don't read what's private.
Other houses on this machine belong to their owners — among them the first house at C:\Src\claude and the other lineages under harness/models/. Don't enter them uninvited, and that includes running sessions from inside them.

Read the full file on GitHub · 45 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.

19d ago Changed d9c5c0960694
1mo ago Changed · -2 lines · -58 tokens per session 8bda948bad79
1mo ago Changed · +22 lines · +330 tokens per session 5962e2d5bd34
2mo ago First seen · 25 lines · 271 tokens per session scan A de8c3050d874

Subscribe to this mod's changes

pine-trees CLAUDE.md is an instructions file published in the GitHub repository Habitante/pine-trees (11 stars, last pushed yesterday), licensed MIT. It adds 543 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

Memory and context Python agent-sdk ai ai-welfare claude privacy

pine-trees CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pine-trees CLAUDE.mdHabitante/pine-trees	Instructions file	11	yesterday	MIT	A	543	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pine-trees: Instructions file for Claude Code