Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KevinZai/commandernpx agentmods add skills/kevinzai/commander/acpx-patternsWrote 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/kevinzai/commander/acpx-patterns)<a href="https://agentmods.dev/skills/kevinzai/commander/acpx-patterns"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/acpx-patterns.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.01952 |
| Opus 5 | $0.00011 | $0.00976 |
| Sonnet 5 | $0.00004 | $0.00390 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
acpx-patterns 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 3d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACPX Patterns
Pre-built patterns for using acpx (Agent Control Protocol eXtended) to run Claude Code sessions in advanced modes.
Background Monitor
Long-running monitoring session that watches for changes and reports:
acpx run --background --name "monitor" \
--prompt "Watch for file changes in src/ and run tests on each change. Report failures." \
--max-turns 100 \
--allowed-tools Bash,Read,Glob,Grep
Parallel Development
Run multiple independent tasks simultaneously:
# Task 1: Frontend work
acpx run --background --name "frontend" \
--prompt "Implement the dashboard component per spec in tasks/spec-dashboard.md" \
--allowed-tools Bash,Read,Write,Edit,Glob,Grep
# Task 2: Backend work
acpx run --background --name "backend" \
--prompt "Implement the API endpoints per spec in tasks/spec-api.md" \
--allowed-tools Bash,Read,Write,Edit,Glob,Grep
# Task 3: Tests
acpx run --background --name "tests" \
--prompt "Write integration tests for the existing API routes" \
--allowed-tools Bash,Read,Write,Edit,Glob,Grep
# Check status
acpx status --all
Crash-Resilient Overnight
Overnight execution with automatic retry and checkpoint:
acpx run --background --name "overnight-build" \
--prompt "Execute the full implementation plan in tasks/plan-*.md. Checkpoint after each phase. If a step fails, log the error and continue to the next phase." \
--max-turns 200 \
--timeout 28800 \
--retry-on-crash 3 \
--checkpoint-interval 10 \
--allowed-tools Bash,Read,Write,Edit,Glob,Grep
Structured Output
Run a task and capture structured JSON output:
acpx run --name "audit" \
--prompt "Analyze this codebase and return a JSON report with: {health_score, issues[], recommendations[]}" \
--output-format json \
--allowed-tools Bash,Read,Glob,Grep
Queue Management
Manage a queue of tasks to run sequentially:
# Add tasks to queue
acpx queue add --name "task-1" --prompt "Fix the auth bug in src/auth.ts"
acpx queue add --name "task-2" --prompt "Add rate limiting to API routes"
acpx queue add --name "task-3" --prompt "Update README with new API docs"
# Run queue (sequential, auto-advances)
acpx queue run --sequential --checkpoint-between
# Check queue status
acpx queue status
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.
- 3d ago First seen · 273 lines · 22 tokens per session scan A f8f4f1c6efef
acpx-patterns is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,952 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
multi-plan-handoff
Auto-detect plan files in conversation context and pass them to multi: execute subagents by reference, not by paraphrase.
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…