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 | $0.15631 | $0.15631 |
| Opus 5.5 | $0.06252 | $0.06252 |
| Sonnet 5.5 | $0.03126 | $0.03126 |
| Haiku 4.5 | $0.01563 | $0.01563 |
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 1mo 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 — 159 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.
- 1mo ago Changed · +2 lines · +1,413 tokens per session 0d4337641dbb
- 2mo ago Changed · +4 lines · +2,298 tokens per session 98ff26ecb67b
- 2mo 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 (136 stars, last pushed 1mo ago), licensed MIT. It adds 15,631 tokens to every session, about $0.0625 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.
es-de-companion CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| es-de-companion CLAUDE.mdRobZombie9043/es-de-companion | Instructions file | 136 | 1mo ago | MIT | A | 15,631 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |