entroly: Instructions file for Claude Code

CLAUDE.md

entroly CLAUDE.md is an instructions file for Claude Code from juyterman1000/entroly. It costs 3,626 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for AI agents working on Entroly, an auditable system for controlling the context given to agents. They define its workflow and trust requirements.

In plain words
What is it for?
Planning and implementing Entroly changes, checking receipts and reversible compression, testing affected areas, and preserving rollback and release checks.
Why use it?
They give agents a repeatable process for clarifying, planning, building, reviewing, testing, shipping, and recording changes without weakening auditability or verification.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is juyterman1000/entroly's own configuration. It tells Claude Code how to work on entroly 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 entroly configures →

Reuse

Borrowing it

Nothing to install: this file belongs to juyterman1000/entroly. 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/juyterman1000/entroly/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/juyterman1000/entroly

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 entroly CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/juyterman1000/entroly/claude-md.svg)](https://agentmods.dev/instructions/juyterman1000/entroly/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/juyterman1000/entroly/claude-md"><img src="https://agentmods.dev/badge/instructions/juyterman1000/entroly/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,626 This file is loaded in full into every session.
When invoked 3,626 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 $0.03626 $0.03626
Opus 5 $0.01813 $0.01813
Sonnet 5 $0.00725 $0.00725
Haiku 4.5 $0.00363 $0.00363

Measured today against content hash e1d0801b49fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

entroly 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 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.

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 · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 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.

Gstack Operating Protocol

Use a gstack-style workflow for non-trivial Entroly work: Think -> Plan -> Build -> Review -> Test -> Ship -> Reflect.

Entroly is an auditable context-control plane for AI agents, not a normal utility library. Every change must preserve trust: receipts must remain explainable, compression must remain reversible, verification must fail closed, and release automation must stay boring.

Default workflow

  1. Clarify the smallest useful user outcome before writing code.
  2. Challenge the product claim: what is the real wedge, what can be cut, and what evidence would prove it?
  3. Lock architecture before implementation: data flow, state transitions, failure modes, and test matrix.
  4. Implement the smallest safe change.
  5. Review for production bugs, trust regressions, packaging breakage, and overclaims.
  6. Run targeted tests first, then expand to release tests if packaging/native surfaces changed.
  7. Ship with a rollback path and exact verification commands.
  8. Record any fragile release or test behavior so the next agent does not repeat it.

If gstack skills are installed, prefer this sequence:

/office-hours -> /plan-ceo-review -> /plan-eng-review -> implement -> /review -> /qa or targeted tests -> /ship -> /retro

If gstack is not installed, follow the same workflow manually.

Entroly trust invariants

Do not merge a change that weakens these invariants:

  • Receipt honesty: selected context, omitted evidence, risks, hashes, and token ratios must be inspectable.
  • Reversibility: compressed or summarized context must remain traceable back to source spans.
  • Fail-closed verification: WITNESS, RAVS, and native-status checks must degrade safely, not silently claim confidence.
  • Local-first operation: no surprise remote calls for ranking, receipts, verification, or diagnostics. The single carve-out is engine repair: when the native engine is missing, entroly/self_heal.py installs entroly-core from PyPI before measuring, because without it selection never reads the query and any reported saving is budget arithmetic. It is a package install — no code, prompts, or telemetry leave the machine — it is skipped when the engine is present, and ENTROLY_NO_SELF_HEAL=1 disables it. Do not extend this carve-out to anything else, and never repair from an import path.
  • Cache stability: prompt prefixes should remain byte-stable unless intentionally changed.
  • Release consistency: Python, Rust, WASM, npm, Homebrew, docs, and native minimum versions must agree.
  • Benchmark honesty: claims must include baseline, token budget, workload, and caveats.

Read the full file on GitHub · 332 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 · +49 lines · +693 tokens per session e1d0801b49fb
  2. 8d ago First seen · 283 lines · 2,933 tokens per session scan A f6f194fcce5f

Subscribe to this mod's changes

entroly CLAUDE.md is an instructions file published in the GitHub repository juyterman1000/entroly (443 stars, last pushed today), licensed Apache-2.0. It adds 3,626 tokens to every session, about $0.0181 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.

Related

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.

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

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

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

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

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