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/max-listov/ccmux/claude-mdgit clone --depth 1 https://github.com/max-listov/ccmuxWrote 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/max-listov/ccmux/claude-md)<a href="https://agentmods.dev/instructions/max-listov/ccmux/claude-md"><img src="https://agentmods.dev/badge/instructions/max-listov/ccmux/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 | $0.03273 | $0.03273 |
| Opus 5 | $0.01636 | $0.01636 |
| Sonnet 5 | $0.00655 | $0.00655 |
| Haiku 4.5 | $0.00327 | $0.00327 |
Grade A, and why
ccmux 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 today.
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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccmux — project conventions
🔒 This is a PUBLIC repo — never leak the maintainer's private identifiers
Everything committed here (code, docs, backlog, tests, comments) is published. NEVER write into
this repo the maintainer's private fleet/machine names, hostnames, machine rcPrefix values,
concrete session names, project names, usernames, email, or absolute home paths. This holds even
in examples, motivation text, and backlog notes.
- Use generic placeholders instead:
agent-A/agent-Bfor sessions,host-A/host-Bfor machines,<target>/<name>for arguments,/Users/u/...or~/...for paths,<prefix>for an rcPrefix. - Before finishing any edit that touches
.md/comments, sweep the changed lines for private tokens. - If unsure whether a term is private, treat it as private and use a placeholder.
bun scripts/check-publication.ts checks current tracked/untracked Markdown as part of the full
gate. The pre-commit hook uses the same structural rules on staged additions in every file type.
It rejects concrete home-path shapes, deployment-machine label shapes, operational frontmatter
and UUID-addressed return routes; diagnostics show only file, line and rule. Generic placeholders
remain valid. This is not an exhaustive private-name detector or a historical Git/asset scan:
review arbitrary prose manually, and never embed private identifiers in the checker itself.
Commit messages carry the same rule — and one leak the list above missed
Claude Code appends Co-Authored-By: Claude … and Claude-Session: https://claude.ai/code/session_…
to commit messages by default. That default lives in the agent's environment, not in this repo,
so it is not something a session decides to do — it is something a session must be stopped from
doing. Claude-Session is a live link to the maintainer's private working session, published in a
public repository: more sensitive than any name in the list above, and absent from it. Two commits
reached main carrying both before this was written down.
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.
- today Changed · +52 lines · +836 tokens per session a6257c599896
- 5d ago First seen · 212 lines · 2,437 tokens per session scan A 8a6d67e2f05d
ccmux CLAUDE.md is an instructions file published in the GitHub repository max-listov/ccmux (2 stars, last pushed today), licensed MIT. It adds 3,273 tokens to every session, about $0.0164 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
mirage CLAUDE.md
Claude Code instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
lade AGENTS.md
AGENTS.md instructions for zifeo/lade, covering agents.md, build & test, house rules, project layout and maintainer note.
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
claudebar CLAUDE.md
Claude Code instructions for mryll/claudebar, covering claude.md, non-obvious rules and hardening invariants.
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
claude-wrapper CLAUDE.md
Instructions for smartwatermelon/claude-wrapper, covering claude.md, what this is, commands, run tests and lint.