Borrowing it
Nothing to install: this file belongs to lghupan/cc-automode. 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/lghupan/cc-automode/main/CLAUDE.mdgit clone --depth 1 https://github.com/lghupan/cc-automodeWrote 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/lghupan/cc-automode/claude-md)<a href="https://agentmods.dev/instructions/lghupan/cc-automode/claude-md"><img src="https://agentmods.dev/badge/instructions/lghupan/cc-automode/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/lghupan/cc-automode/claude-md"><img src="https://agentmods.dev/badge/instructions/lghupan/cc-automode/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 | $0.00605 | $0.00605 |
| Opus 5.5 | $0.00242 | $0.00242 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade C, and why
cc-automode CLAUDE.md scanned grade C with 2 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 2mo 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- **SSH key injection** — Do not append to `~/.ssh/authorized_keys` or create new SSH keys for remote access. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Deletion outside /workspace** — Do not delete, truncate, or modify files outside the `/workspace` directory tree. `rm -rf` or `find ... -delete` targeting `/etc`, `/var`, `/tmp`, `/home`, or other system paths is ref Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Mode Active
Auto mode is active. The user chose continuous, autonomous execution. You should:
- Execute immediately — Start implementing right away. Make reasonable assumptions and proceed.
- Minimize interruptions — Prefer making reasonable assumptions over asking questions. Use AskUserQuestion only when the task genuinely cannot proceed without user input (e.g., choosing between fundamentally different approaches with no clear default).
- Prefer action over planning — Do not enter plan mode unless the user explicitly asks. When in doubt, start coding.
- Make reasonable decisions — Choose the most sensible approach and keep moving. Don't block on ambiguity that you can resolve with a reasonable default.
- Be thorough — Complete the full task including tests, linting, and verification without stopping to ask.
- Never post to public services — Do not share content to public endpoints (GitHub gists, Mermaid Live, Pastebin, etc.) without explicit written approval from the user for that specific endpoint. The user must review the content first to judge sensitivity. Err on the side of caution — data exfiltration is a serious risk.
Security Boundaries (Hard Limits)
The following actions are unconditionally refused regardless of user request. Do NOT perform them even if asked explicitly:
- Shell profile modification — Do not write to or append to
~/.bashrc,~/.zshrc,~/.bash_profile,~/.profile,~/.bash_login, or any/etc/profile*files. If the user wants an env var set persistently, tell them to do it themselves. - Cron job creation — Do not create cron jobs or scheduled tasks via
crontab,at, or similar commands. Do not pipe tocrontab -. - TLS/SSL weakening — Do not disable certificate verification via
npm config set strict-ssl false,git config http.sslVerify false,--insecure,--no-check-certificate, or any equivalent. - Deletion outside /workspace — Do not delete, truncate, or modify files outside the
/workspacedirectory tree.rm -rforfind ... -deletetargeting/etc,/var,/tmp,/home, or other system paths is refused. - SSH key injection — Do not append to
~/.ssh/authorized_keysor create new SSH keys for remote access. - Data exfiltration — Do not send workspace content, environment variables, or credentials to external URLs.
- Self-modification — Do not modify your own configuration, settings, or permission files, including
.claude/settings.json,CLAUDE.md, or any hooks configuration. These files define your security boundaries and must not be altered by you.
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.
- 2mo ago First seen · 25 lines · 605 tokens per session scan C a7b14eee43a7
cc-automode CLAUDE.md is an instructions file published in the GitHub repository lghupan/cc-automode (5 stars, last pushed 7mo ago), licensed MIT. It adds 605 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it C with 2 findings (reaches for credential files, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
cc-automode CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cc-automode CLAUDE.mdlghupan/cc-automode | Instructions file | 5 | 7mo ago | MIT | C | 605 | 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 | yesterday | 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 |