Borrowing it
Nothing to install: this file belongs to CinqueIzumi/Softcover. 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/CinqueIzumi/Softcover/main/CLAUDE.mdgit clone --depth 1 https://github.com/CinqueIzumi/SoftcoverWrote 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/cinqueizumi/softcover/claude-md)<a href="https://agentmods.dev/instructions/cinqueizumi/softcover/claude-md"><img src="https://agentmods.dev/badge/instructions/cinqueizumi/softcover/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/cinqueizumi/softcover/claude-md"><img src="https://agentmods.dev/badge/instructions/cinqueizumi/softcover/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 | $0.01710 | $0.01710 |
| Opus 5.5 | $0.00684 | $0.00684 |
| Sonnet 5.5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
Softcover 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project overview
Softcover is a Kotlin Multiplatform / Compose Multiplatform client for Hardcover.app, a
book tracking platform, on Android (SDK 26+), iOS and desktop (JVM). Shared UI and logic live in commonMain.
Engineering principles
Never take shortcuts; never propose the "less clean" option. When two solutions are available — a structurally clean one and a smaller-diff pragmatic one — pick the clean one and present it as the recommendation. Do not surface "less clean / pragmatic / repository-aggregator / pass-through delegation / cross-feature data-source reach" alternatives as primary recommendations. Mention a smaller-diff fallback only when the user explicitly asks for the cheaper path or when the clean option is genuinely out of scope. Cost (larger diff, more files touched, follow-up moves) is not a reason to defer; surface the cost transparently and proceed with the right structure unless told otherwise.
Working in this repo
- Session loop:
docs/working/ACTIVE.md→ the active tracker's## Nowblock → do one step →/handoff→ the user runs/clear. One step per session. - Routing: a change touching ≤3 existing files, with no new file and no public API change, is done in the
main conversation. Anything bigger goes to
softcover-implementer. Tests always go tosoftcover-test-writer. Before reporting substantial work done (a new file or module, a multi-file change, or any layout / state / data-flow change), runsoftcover-reviewerafter the build succeeds. Briefs followdocs/reference/agent-briefs.md(enforced by a hook). - The main conversation directs. No multi-step Gradle loops and no paging through large files in it. Gradle output is summarised automatically; the full log is at the printed path.
Build & test
./gradlew assembleDebug # Debug build
./gradlew assembleRelease # Release build
./gradlew test # :app / :desktopApp unit tests only — no KMP suites
./gradlew testAndroidHostTest --continue # KMP unit tests
./gradlew :smoketest:pixelApi36MinifiedAndroidTest # Device suite, R8-minified app (needs HARDCOVER_SMOKE_TOKEN)
./gradlew :app:checkR8KeepContract # R8 keep contract on the release and minified builds
./gradlew lint # Android Lint
./gradlew ktlintFormat # Auto-fix layout rules
./gradlew styleCheck # detekt + ktlint gates
./gradlew check koverXmlReport -x lint # PR gate: what CI runs on PRs into release/*
./gradlew check # Everything except buildHealth; iOS compiles on macOS only
./gradlew check buildHealth # Full gate: CI on every push to main, release/*, hotfix/* and chore/*
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.
- 6d ago Changed · +6 tokens per session 7b1e17366258
- 12d ago Changed · +8 lines · +233 tokens per session 5ee54456c2f3
- 1mo ago Changed · -55 lines · -3,029 tokens per session 3e70bdd47d5d
- 2mo ago First seen · 140 lines · 4,500 tokens per session scan A e638a81b3838
Softcover CLAUDE.md is an instructions file published in the GitHub repository CinqueIzumi/Softcover (16 stars, last pushed yesterday), licensed MIT. It adds 1,710 tokens to every session, about $0.0068 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.