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/wangnov/claude-code-statusline-pro/claude-mdgit clone --depth 1 https://github.com/Wangnov/claude-code-statusline-proWrote 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/wangnov/claude-code-statusline-pro/claude-md)<a href="https://agentmods.dev/instructions/wangnov/claude-code-statusline-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/wangnov/claude-code-statusline-pro/claude-md.svg" alt="Measured on agentmods" 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 | $0.00963 | $0.00963 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
claude-code-statusline-pro 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Statusline Pro - 开发指引
开发流程
在完成任何开发任务并提交修改之前,执行完整 CI 检查:
make ci
这将按顺序执行以下步骤:
make fix- 自动应用编译器建议make fmt- 格式化代码make clippy-fix- Clippy 自动修复make clippy- Clippy 严格检查make check- 编译检查make test- 运行测试make build- Release 构建
若某一步失败,应先修复问题并重新执行 make ci,直至全部通过。
常用命令
| 命令 | 说明 |
|---|---|
make ci |
完整 CI 流程(推荐提交前执行) |
make quick |
快速检查(跳过自动修复) |
make test |
仅运行测试 |
make bump已废弃,版本号由cargo release管理,见下文。
发布流程
本项目采用 cargo-release + cargo-dist 两阶段发布流程。crates.io 由 maintainer 本地推送,CI 只负责二进制构建与分发。
前置条件
- 本地已登录 crates.io(
cargo login),且当前账号对claude-code-statusline-pro有发布权限 - 仓库已配置
HOMEBREW_TAP_TOKENsecret(推 Homebrew formula 到Wangnov/homebrew-tap)
阶段 1:准备候选版本
# 1. 保证主分支干净
make ci
git checkout main && git pull --ff-only
# 2. 生成版本号 bump 的 release commit(不 publish、不打 tag、不 push)
cargo release <patch|minor|major> --execute --no-publish --no-tag --no-push --no-confirm
# 3. 推送 release commit 到 main
git push origin main
# 4. 在 GitHub Actions 手动触发 "Release candidate" workflow
# 使用 release commit 对应的 ref(默认 main 即可)
# 该 workflow 会用 cargo-dist 构建 6 个平台的 archive 并跑 smoke test
阶段 2:执行正式发布(候选全绿后)
# 5. 依次推 crates.io → 打 tag → 推 tag
cargo release publish --execute --no-confirm
cargo release tag --execute --no-confirm
cargo release push --execute --no-confirm
tag 推送后 CI 自动接管:
release.yml(cargo-dist 生成)→ 6 平台构建 + GitHub Release + Homebrew formula- GitHub Release published 事件触发
build.yml→ 下载 Release 资产 → 组装 npm 包 → 发布(trusted publishing)
发布后验证
gh release view v<X.Y.Z> # GitHub Release 资产齐全?
cargo search claude-code-statusline-pro --limit 1 # crates.io 版本正确?
npm view ccsp version # npm 根包版本正确?
npm view @wangnov/ccsp-linux-x64 version # 平台包抽检
失败状态清理
若候选全绿、crates.io 推送成功,但 tag 触发的 release.yml 失败:
# 删 tag(本地 + 远端),修完 release.yml 的问题后重新打 tag
git tag -d v<X.Y.Z>
git push origin :v<X.Y.Z>
# 修复 → 在同一 release commit 上
cargo release tag --execute --no-confirm
cargo release push --execute --no-confirm
# crates.io 保持原样;cargo release publish 会识别已发布状态并跳过
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 First seen · 105 lines · 963 tokens per session scan A be5965556dac
claude-code-statusline-pro CLAUDE.md is an instructions file published in the GitHub repository Wangnov/claude-code-statusline-pro (235 stars, last pushed 19d ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 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
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
aicm 06_rust-rule.instructions.md
Instructions for morooka-akira/aicm, covering rust 固有のルール, 実装時の注意点, エラーハンドリング, 型システムの活用 and パフォーマンス特徴.