agentmods.dev

FixThis: Instructions file for Claude Code

CLAUDE.md

FixThis CLAUDE.md is an instructions file for Claude Code from beyondwin/FixThis. It costs 583 tokens per session, scanned A, original, MIT.

Project instructions for FixThis, with pointers to its Kotlin server, JavaScript console, Android sample app, build checks, and communication rules between components.

In plain words
What is it for?
Use them when modifying the server, console, sample app, restart workflow, or bridge protocol, and when preparing changes for review.
Why use it?
They identify the required verification steps and the files that must stay synchronized when the communication protocol changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

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

not rated 5repo changed 1mo ago A scan 583 tokens original MIT
View source ↗ beyondwin/FixThis
Reuse

Borrowing it

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

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 FixThis CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/beyondwin/fixthis/claude-md/github.svg)](https://agentmods.dev/instructions/beyondwin/fixthis/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/beyondwin/fixthis/claude-md"><img src="https://agentmods.dev/badge/instructions/beyondwin/fixthis/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.

agentmods 80×15 button for FixThis CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/beyondwin/fixthis/claude-md"><img src="https://agentmods.dev/badge/instructions/beyondwin/fixthis/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 583 This file is loaded in full into every session.
When invoked 583 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 $0.00583 $0.00583
Opus 5.5 $0.00233 $0.00233
Sonnet 5.5 $0.00117 $0.00117
Haiku 4.5 $0.00058 $0.00058

Measured 1mo ago against content hash dc8131a05ece, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FixThis 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.

CLAUDE.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FixThis — Claude Code Project Memory

Entry point for Claude Code in this repository. Follow AGENTS.md.

Pointers

  • Build, test, console rebundle, lint commands → CONTRIBUTING.md
  • Final verification before PRs → run the full Gradle matrix, console asset check, console JS syntax check, console JS harnesses, and git diff --check from CONTRIBUTING.md.
  • Restart loop after Kotlin changes → run bash scripts/restart-console.sh (add --with-app to also reinstall the sample APK). Kotlin server code is pinned in the JAR; the console JS is live-reloaded under --console-assets-dir. Full flag list in CONTRIBUTING.md § Console Inner Loop.
  • Bridge protocol changes must update BridgeProtocol.VERSION, the console MinimumSupportedProtocolVersion, and the mirrored constants in BridgeClient.kt and ServerVersionRoutes.kt. BridgeProtocolVersionSyncTest (:fixthis-mcp:test) enforces equality across all four sites at CI time. Full procedure: docs/reference/bridge-protocol.md.
  • Architecture invariants (core has no MCP/CLI/Android dep, persisted JSON field names are compatibility contracts, sidekick hosts no HTTP/MCP server) → docs/architecture/overview.md and docs/architecture/adr/.
  • Console UI iteration — pass --console-assets-dir to read HTML/CSS/JS from source instead of the packaged JAR; rebundle JS via node scripts/build-console-assets.mjs after edits (produces minified app.js ≤ 247,000 B raw / 62,500 B gzip, an app.js.map source map for DevTools, and a console-build-meta.json sidecar inlined as window.FixThisConsoleConfig.buildMeta at serve time), then verify with node scripts/build-console-assets.mjs --check. Details in docs/reference/feedback-console-contract.md.
  • Connected tests — require an unlocked interactive emulator or device. Locked physical devices can still report device in adb while failing Compose hierarchy discovery. See docs/guides/troubleshooting.md.

Read the full file on GitHub · 37 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. 1mo ago Changed · -2 lines · -22 tokens per session dc8131a05ece
  2. 2mo ago First seen · 39 lines · 605 tokens per session scan A ede308c06378

Subscribe to this mod's changes

FixThis CLAUDE.md is an instructions file published in the GitHub repository beyondwin/FixThis (5 stars, last pushed 9d ago), licensed MIT. It adds 583 tokens to every session, about $0.0023 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 2026-08-31.

androidandroid-mcpandroid-toolsdeveloper-toolsjetpack-composemcp
Related

FixThis CLAUDE.md compared with instructions from other repositories

FixThis CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
FixThis CLAUDE.mdbeyondwin/FixThisInstructions file59d agoMITA583Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode