Borrowing it
Nothing to install: this file belongs to RobZombie9043/es-de-companion. 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/RobZombie9043/es-de-companion/master/CLAUDE.mdgit clone --depth 1 https://github.com/RobZombie9043/es-de-companionWrote 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/robzombie9043/es-de-companion/claude-md)<a href="https://agentmods.dev/instructions/robzombie9043/es-de-companion/claude-md"><img src="https://agentmods.dev/badge/instructions/robzombie9043/es-de-companion/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.
<a href="https://agentmods.dev/instructions/robzombie9043/es-de-companion/claude-md"><img src="https://agentmods.dev/badge/instructions/robzombie9043/es-de-companion/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.14218 | $0.14218 |
| Opus 5 | $0.07109 | $0.07109 |
| Sonnet 5 | $0.02844 | $0.02844 |
| Haiku 4.5 | $0.01422 | $0.01422 |
Grade A, and why
es-de-companion 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 5d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository. This project is a ground-up rebuild of ES-DE Companion, a dual-screen companion app for the ES-DE emulation frontend, using modern Android best practices.
This document is deliberately weighted toward structure, layering, and code quality rather than a fixed feature spec. The core state pipeline is foundational and must be built to a higher standard of rigor than everything else in the app.
The One Thing That Has To Be Rock Solid
Everything this app does depends on correctly understanding what ES-DE is currently doing. The pipeline is:
es_log.txt (raw text, growing/truncating file)
→ tail new lines
→ filter for "Scripting::fireEvent():" lines
→ parse into a typed Event
→ reduce events into a single current AppState
→ AppState drives everything downstream (media lookup, UI, widgets, whatever comes later)
This pipeline is the foundation everything else is built on. Treat it accordingly:
- It lives entirely in
domain, as plain Kotlin with no Android framework dependencies where at all possible — the parsing and state-reduction logic should be testable with plain unit tests against fixture log lines, with no emulator, no instrumentation, no mocked Android classes. - It should have the best test coverage of anything in the codebase. Every event type, malformed/unexpected line, empty-args case, and the truncate-on-restart case need explicit tests.
- Resist the urge to let UI or media-resolution concerns leak into this layer. Its only job is: raw log text in, correct
AppStateout. Nothing else should influence it, and it should not know anything about widgets, screens, or file paths for media. - If this layer has a bug, the entire app is wrong regardless of how polished anything built on top of it is. Prioritize correctness and clarity here over cleverness or premature abstraction.
- Cold start is not "replay the last event." A freshly-launched app has no state to reduce onto, and context-dependent events (e.g.
screensaver-end, which needs to know what was active before the screensaver started) produce the wrong result if the reducer only sees the single most recent line.EsdeLogFileRepositoryinstead finds the last self-contained ("anchor") event and replays forward from there, growing its read window backward until it finds one or hits the start of the file. SeeEsdeLogFileRepositoryTestfor the anchor-replay cases. That replay is also skipped ifes_log.txt'slastModified()predates the current boot — a device reboot can auto-start this app (it carries aHOMEintent filter for secondary-display placement) before ES-DE has (re)written the log this session, so an anchor found in a not-yet-touched-since-boot file is guaranteed to be a leftover from before the reboot, not current truth. - The derived
AppStatestream is shared, not rebuilt per subscriber.ObserveAppStateUseCasecomputes its reducer fold exactly once, at construction, as an application-scopedStateFlow— not fresh on everyinvoke()call. See Known Gotchas for why a naive per-callscan()silently produces stale/Idlestate for late-joining subscribers.
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.
- 5d ago Changed · +4 lines · +2,298 tokens per session 98ff26ecb67b
- 11d ago First seen · 153 lines · 11,920 tokens per session scan A 128774775210
es-de-companion CLAUDE.md is an instructions file published in the GitHub repository RobZombie9043/es-de-companion (117 stars, last pushed 6d ago), licensed MIT. It adds 14,218 tokens to every session, about $0.0711 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
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.
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).
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.
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).
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.