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 skills add DJRHails/dotfiles --skill cmux-rebuildgit clone --depth 1 https://github.com/DJRHails/dotfilesWrote 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/skills/djrhails/dotfiles/cmux-rebuild)<a href="https://agentmods.dev/skills/djrhails/dotfiles/cmux-rebuild"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/cmux-rebuild.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 5.1 | $0.00245 | $0.04134 |
| Opus 5 | $0.00122 | $0.02067 |
| Sonnet 5 | $0.00049 | $0.00827 |
| Haiku 4.5 | $0.00024 | $0.00413 |
Grade A, and why
cmux-rebuild 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux durable sessions
Dev work lives in zellij sessions named cmux-<host>-<id>. Remote hosts (bonbon, taffy)
are reached over mosh (survives high-redraw TUIs; cmux's ws relay adds per-keystroke latency)
— each surfaced as a cmux tab running mosh <host> -- zellij attach <session>. The local host
(trifle) auto-attaches a local zellij wrapper in every terminal surface. Zellij sessions persist
across everything; only the cmux surfaces and mosh transports come and go.
Code: modules/zellij/ — mosh-zellij.zsh (ssh::durable picker + zellij::resume),
durable-remote.sh (remote menu/preview/reap), auto-attach.zsh (attach + de-nest handoff).
claude::resume / pi::resume (modules/claude, modules/pi aliases) resolve a session id to its
transcript, cd to its recorded cwd, and route the owning config dir.
TMPDIR rule: every local zellij invocation needs TMPDIR=/tmp — the socket dir follows
TMPDIR, and a surface shell's macOS default (/var/folders/…) silently sees zero sessions. The
scripts force it; do the same in ad-hoc commands.
Attach: ssh::durable and zellij::resume
ssh::durable <host> — fzf picker of the host's live sessions (<cwd> · <AI title> with a dim
searchable id tail). Green ● = connected, computed exactly and fresh on each open: a local
mosh-client is talking to that session's mosh-server UDP port (CPU-jiffie sampling was tried and
abandoned — keepalive work is sub-jiffie). enter attach · ctrl-r re-summarise · ctrl-x kill
· esc fresh. Non-interactive: --list, --attach <session>, --query <str>, --reap.
zellij::resume <session> — the local analogue: stages the attach, de-nests the auto-attach
wrapper (deleting its husk), and execs zellij attach <session>.
Rebuild after a cmux restart / mass disconnect
python3 scripts/rebuild-durable.py [hosts...] --dry-run # plan (hosts default: bonbon taffy <local>)
python3 scripts/rebuild-durable.py [hosts...] # create surfaces + send attaches
python3 scripts/rebuild-durable.py [hosts...] --retry # re-send to idle surfaces for stragglers
python3 scripts/rebuild-durable.py [hosts...] --retitle # rename connected tabs to short ids
python3 scripts/rebuild-durable.py [hosts...] --bind # backfill cmux resume bindings
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +11 lines 9394341ce67f
- 3d ago Changed · +29 lines · +13 tokens per session e7bd9899a47c
- 4d ago Changed · +1 lines 6637e408ffc6
- 8d ago First seen · 188 lines · 232 tokens per session scan A 40519da32186
cmux-rebuild is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed today), licensed MIT. It adds 245 tokens to every session and 4,134 once invoked, about $0.0012 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 skills, from other repositories
todoist-cli
Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the td CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.
autopilot-batch
Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and never below the build (Opus reviews Sonnet and Opus builds, Fable reviews Fable builds).
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
qa-handoff
Generate a hands-on QA testing guide as a self-contained HTML page — for Rails apps or static (Hugo) sites. --publish uploads the HTML to the project's configured QA host.
walkthrough
Generate a hands-on browser walkthrough of a PR's user-facing changes to exercise before review; --publish posts the final version to the PR for QA.
dustoff
Assess a project that's been dormant for months and produce a prioritized re-entry plan — lifecycle stage, what's stale or broken, and how far the project's tooling has drifted from current conventions — delegating every fix to the skill that owns it, and optionally capturing the plan as a tracking issue that survives…