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 commands/akka/ai-marketplace/setupgit clone --depth 1 https://github.com/akka/ai-marketplaceWrote 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/commands/akka/ai-marketplace/setup)<a href="https://agentmods.dev/commands/akka/ai-marketplace/setup"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/setup.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 | $0.00049 | $0.03471 |
| Opus 5 | $0.00024 | $0.01736 |
| Sonnet 5 | $0.00010 | $0.00694 |
| Haiku 4.5 | $0.00005 | $0.00347 |
Grade D, and why
setup scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Linux (apt fallback):** Show `sudo apt install openjdk-21-jdk` to the user and ask permission before executing. Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Linux (preferred):** If SDKMAN is not available, install it with `curl -s "https://get.sdkman.io" | bash` then `source "$HOME/.sdkman/bin/sdkman-init.sh"`. Then execute `sdk install java 21-tem`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Linux (preferred):** If SDKMAN is not available, install it with `curl -s "https://get.sdkman.io" | bash` then `source "$HOME/.sdkman/bin/sdkman-init.sh"`. Then execute `sdk install java 21-tem`. How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Purpose
/akka-specify:setup detects the user's environment, installs all missing dependencies,
scaffolds an Akka project, and leaves the user ready to develop — with zero
prerequisites beyond having an AI coding agent installed.
The skill is idempotent and re-runnable. On first run it performs full setup. On subsequent runs it operates in repair/upgrade mode.
Execution Instructions
FIRST: Test if you have shell access by executing echo "bash-ok" using the Bash tool.
If Bash is available: Execute all commands yourself. Do NOT ask the user to run
commands or paste output. The only exceptions are commands requiring sudo (show the
command and ask permission first) and akka code token (which opens a browser).
If Bash is NOT available (plugin permission limitation): This skill was loaded from a plugin, which currently does not grant shell access. Tell the user:
"The setup skill needs shell access to install dependencies and scaffold your project. Please allow Bash access for this skill and try again. You can do this by approving the permission prompt when it appears, or by updating your Claude Code settings."
STOP HERE if Bash is not available. Do not proceed with the phases below.
Phases 1–4 use only bash commands — the Akka CLI is not yet installed, so MCP tools
are unavailable. After Phase 4, delegate to akka CLI commands.
Work through each phase sequentially. Skip phases where the check shows the dependency is already satisfied. Report progress to the user after each phase.
Phase 1: Environment Detection
Execute the following to detect the platform:
- Run
uname -sanduname -mto determine OS and architecture. - Run
echo $SHELLto determine the shell. - On Linux, run
cat /etc/os-release 2>/dev/null | grep -E '^(ID|ID_LIKE)='for the distro. - Check which package managers are available by running
command -v brew,command -v apt,command -v dnf,command -v pacman,command -v winget,command -v scoop,command -v sdk.
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.
- 5d ago First seen · 299 lines · 49 tokens per session scan D 88dcaccff551
setup is a command published in the GitHub repository akka/ai-marketplace (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,471 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
spec-kitty.implement
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
bench-capture
Score the 2 bench variant folders for one size (build/acceptance/regression/conventions/capture + rubric + cross-solution review), record, report, and reset.
autospec.plan
Generate YAML implementation plan from feature specification.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.