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/mdsakalu/agent-plugins/onboardgit clone --depth 1 https://github.com/mdsakalu/agent-pluginsWhat 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 | $0.00017 | $0.03018 |
| Opus 5 | $0.00009 | $0.01509 |
| Sonnet 5 | $0.00003 | $0.00604 |
| Haiku 4.5 | $0.00002 | $0.00302 |
Grade D, and why
onboard scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. Read `~/.claude/settings.json` and check for the `statusLine` key: Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <CACHE_TARGET> How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up the workspace plugin — walk the user through dependencies, configuration, and optional features.
This is an interactive onboarding wizard. Use AskUserQuestion for every decision point. Explain why each step matters before doing it. The command is idempotent — safe to re-run.
The user's request: $ARGUMENTS
Key Variables
- Plugin root:
${CLAUDE_PLUGIN_ROOT} - Metarepo root: parent directory of plugin root. Resolve it:
Do NOT readMETAREPO=$(cd "${CLAUDE_PLUGIN_ROOT}/.." && pwd)~/.claude/workspace-config.json— this command creates that file.
If the user passes --check, run in check-only mode: report status of all phases without making any changes.
Phase 1: Dependencies
Explain: "Let me check the tools this plugin needs. Required tools are used by every command; optional tools enable specific features."
Required tools
Check each with command -v <tool>. For each, show the path if found, or install instructions if missing:
| Tool | Purpose | Install if missing |
|---|---|---|
jj |
Jujutsu version control — the workspace system is built on JJ workspaces | brew install jj |
jq |
JSON processing — used by hooks and scripts for metadata | brew install jq |
gh |
GitHub CLI — fetches PR info, discovers repos | brew install gh, then gh auth login |
git |
Git — underlying VCS for colocated repos | xcode-select --install |
If any required tool is missing, ask via AskUserQuestion:
- "Continue anyway" — proceed (some commands won't work)
- "Stop here" — abort so they can install first
Optional tools
Check each. Report status but do not block:
| Tool | Check | Purpose | Install if missing |
|---|---|---|---|
zmx |
command -v zmx |
Terminal session multiplexer — required for /workspace:cd workspace switching |
brew install mdsakalu/tap/zmx |
zsm |
command -v zsm |
TUI for managing zmx sessions — list, attach, kill sessions visually | brew install mdsakalu/tap/zsm |
| MarkText | ls ~/Applications/marktext.app/Contents/MacOS/marktext 2>/dev/null |
Markdown editor — opens notes in /workspace:notes |
Download from https://github.com/marktext/marktext |
| VS Code | command -v code |
Code editor — opens workspaces in /workspace:open |
Install VS Code, then Cmd+Shift+P > "Shell Command: Install code command in PATH" |
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 · 272 lines · 17 tokens per session scan D 8224d6f0f391
onboard is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 3,018 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.