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 skills/alleneubank/claude-code/zmxnpx skills add alleneubank/claude-code --skill zmxgit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00034 | $0.00869 |
| Opus 5 | $0.00017 | $0.00434 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
zmx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zmx Process Management
Session Rules
- Check
zmx list --shortbefore creating sessions — duplicates cause port conflicts and confusing output - Derive session name from
git rev-parse --show-toplevel— hardcoded names collide when multiple agent instances run concurrently - Use
zmx runto send commands without attaching —zmx attachblocks the agent's shell and makes it unresponsive - Use separate sessions with a common project prefix for multiple processes
One project = one session prefix. Multiple processes = multiple sessions sharing the prefix.
Session Naming
PROJECT=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" || basename "$PWD")
All subsequent examples assume PROJECT is set. Session names follow ${PROJECT}-<role>:
myapp-server,myapp-tests,myapp-tilt
Starting Processes
SESSION="${PROJECT}-server"
# Idempotent: skip if already running
if ! zmx list --short 2>/dev/null | grep -q "^${SESSION}$"; then
zmx run "$SESSION" 'npm run dev'
fi
For multiple processes, loop over name:command pairs:
for name_cmd in "server:npm run dev" "tests:npm run test:watch"; do
name="${name_cmd%%:*}"
cmd="${name_cmd#*:}"
SESSION="${PROJECT}-${name}"
if ! zmx list --short 2>/dev/null | grep -q "^${SESSION}$"; then
zmx run "$SESSION" "$cmd"
fi
done
Sending Commands
# Run a command in a session (creates session if needed)
zmx run "${PROJECT}-main" 'cat README.md'
# Pipe via stdin
echo "ls -lah" | zmx r "${PROJECT}-main"
Monitoring Output
zmx history "${PROJECT}-server" # full scrollback
zmx history "${PROJECT}-server" | tail -50 # last 50 lines
zmx history "${PROJECT}-server" | rg -i "error|fail" # check for errors
zmx history "${PROJECT}-server" | rg -i "listening|ready" # check for ready
Waiting for Completion
zmx wait "${PROJECT}-tests" # block until done
zmx wait "${PROJECT}-build" "${PROJECT}-lint" # wait for multiple
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.
- 2d ago First seen · 118 lines · 34 tokens per session scan A 0f807b99bb50
zmx is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 869 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…