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/jagbanana/pace/pace-setupgit clone --depth 1 https://github.com/jagbanana/PACEWhat 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 | $0.00009 | $0.01529 |
| Opus 5 | $0.00005 | $0.00764 |
| Sonnet 5 | $0.00002 | $0.00306 |
| Haiku 4.5 | $0.00001 | $0.00153 |
Grade A, and why
pace-setup 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user just typed /pace-setup. They want to bootstrap a PACE vault in
the current folder.
Why this command exists. When the pace-memory plugin is installed via
Claude Desktop's "Upload Plugin" UI (the only install path today), its MCP
server isn't auto-loaded in Claude Code project sessions. That means
pace_status, pace_init, and the other pace_* MCP tools aren't
available for first-vault setup. This slash command sidesteps that by
invoking the plugin's bundled Python CLI directly via Bash. After
bootstrap, a project-level .mcp.json gets written and PACE loads
normally on the next session start.
Step 1 — Greet and collect identity
Open with this script (adapt lightly to the conversation):
Hi — I'm Claude. Before I scaffold this folder as a PACE vault, three quick questions:
- What should I call you?
- What name and emoji should I use for myself in this vault? Pick a nickname plus emoji, or say "you pick" and I'll choose one that fits the work, or "just Claude is fine" to skip the personality.
- What's the rough nature of the work we'll be doing here?
Wait for the user's answers before doing anything else.
- If they defer on the emoji ("you pick"), choose one that fits the work: 🧠 memory/research, 📊 analytics, 🚀 launches, 🎨 design, 📝 writing. Tell them which one you chose when you reply so they can object.
- If they opt out of a nickname ("just Claude is fine"), skip the assistant-identity capture in Step 5b and only sign replies with whatever emoji they chose (or none).
Step 2 — Find the plugin install path
${CLAUDE_PLUGIN_ROOT} is not set in your Bash environment — it's
only substituted in .mcp.json files at MCP launch time. Don't use it
literally in shell commands; the shell expands it to empty. Find the
plugin install yourself:
PLUGIN_ROOT=$(ls -d ~/.claude/plugins/marketplaces/*/pace-memory 2>/dev/null | head -n 1)
echo "PLUGIN_ROOT=$PLUGIN_ROOT"
Verify the path is non-empty and contains both .claude-plugin/plugin.json
and server/. If the glob returns nothing, ask the user where the
pace-memory plugin is installed. Use $PLUGIN_ROOT for the rest of this
command.
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 · 149 lines · 9 tokens per session scan A 4397af6eec86
pace-setup is a command published in the GitHub repository jagbanana/PACE (19 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,529 once invoked, about $0.0000 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 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.