Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/beyondwin/fixthis/claude-mdgit clone --depth 1 https://github.com/beyondwin/FixThisWhat 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 | $0.00605 | $0.00605 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
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 2d 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 — 39 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 working in this repository. See AGENTS.md for the project overview, MCP setup, AI workflow, and constraints — those apply equally to Claude Code.
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 --checkfromCONTRIBUTING.md. - Restart loop after Kotlin changes → run
bash scripts/restart-console.sh(add--with-appto 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 inCONTRIBUTING.md§ Console Inner Loop. - Bridge protocol changes must update
BridgeProtocol.VERSION, the consoleMinimumSupportedProtocolVersion, and the mirrored constants inBridgeClient.ktandServerVersionRoutes.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.mdanddocs/architecture/adr/. - Console UI iteration — pass
--console-assets-dirto read HTML/CSS/JS from source instead of the packaged JAR; rebundle JS vianode scripts/build-console-assets.mjsafter edits (produces minifiedapp.js≤ 225 KiB raw / 58 KiB gzip, anapp.js.mapsource map for DevTools, and aconsole-build-meta.jsonsidecar inlined aswindow.FixThisConsoleConfig.buildMetaat serve time), then verify withnode scripts/build-console-assets.mjs --check. Details indocs/reference/feedback-console-contract.md. - Connected tests — require an unlocked interactive emulator or device.
Locked physical devices can still report
deviceinadbwhile failing Compose hierarchy discovery. Seedocs/guides/troubleshooting.md.
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.
- 2d ago First seen · 39 lines · 605 tokens per session scan A ede308c06378
FixThis CLAUDE.md is an instructions file published in the GitHub repository beyondwin/FixThis (5 stars, last pushed 1mo ago), licensed MIT. It adds 605 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
sceneview copilot-instructions.md
Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
sceneview CLAUDE.md
Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
SeekerClaw CLAUDE.md
Instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.
ukulele-companion AGENTS.md
Instructions for baijum/ukulele-companion, covering agents.md -- ai agent instructions for ukulele companion, project overview, tech stack, package structure and android app (app/src/main/java/com/baijum/ukufretboard/).
AppBootstrapAI CLAUDE.md
Instructions for kelvinkosbab/AppBootstrapAI, covering claude.md, project overview, what's in the box, how to onboard this into a new app project and update an already-managed repo — never a plain re-install.
AppBootstrapAI AGENTS.md
Instructions for kelvinkosbab/AppBootstrapAI, covering agents.md — operating appbootstrapai, golden path — do this, the three situations recommend resolves, what recommend keys on (framework → feature category) and scaffolding a local swift package (separate tool).