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/cdeust/ai-architect-mcp-codebase/_indexgit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00000 | $0.00404 |
| Opus 5 | $0.00000 | $0.00202 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
_index 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.
This is a copy
86% identical to _index — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Commands Index
16 commands across 6 categories. Commands are operational shortcuts that invoke tools, skills, and agents.
Quick Reference
| Command | Category | Description |
|---|---|---|
/agent-list |
agent | List agents by type, shape, or keyword |
/agent-spawn |
agent | Spawn an agent in an isolated worktree |
/agent-status |
agent | Check active agent worktrees |
/skill-run |
skill | Execute a registered skill by name |
/zcommit |
git | Commit with zetetic pre-checks and conventional message |
/zpr |
git | Create PR with review, zetetic checklist, and description |
/zclean |
git | Clean up merged agent worktree branches |
/session-save |
session | Save session context to Cortex + local cache |
/session-recall |
session | Load context from previous session |
/pre-commit |
quality | Run zetetic pre-commit checks manually |
/pre-push |
quality | Run full review on changes since last push |
/qverify |
zetetic | Quick claim verification (fast /verify-claim) |
/qestimate |
zetetic | Quick Fermi bracket (fast /estimate) |
/qreview |
zetetic | Quick review of staged changes (critical only) |
/qdifficulty |
zetetic | Check difficulty book status |
/qintegrity |
zetetic | Quick integrity audit (Feynman-style) |
Installation
Copy commands to your Claude Code commands directory:
# Global (all projects)
cp -r zetetic-team-subagents/commands/* ~/.claude/commands/
# Per-project
mkdir -p .claude/commands
cp -r zetetic-team-subagents/commands/* .claude/commands/
Then type / in Claude Code to see available commands.
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 · 40 lines · 0 tokens per session scan A 103f02e2b1a7
_index is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 404 tokens. A static security scan graded it A with 0 findings. It is 86% identical to _index, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
rb-setup
First-time setup. Configure the LLM API key, or a no-API-key local host runner (Codex / Trae / Claude / any headless CLI) that RepoBrain uses for codebase Q&A and refresh. / 首次 setup，配置 RepoBrain 代码问答与 refresh 所需的 LLM API key，或无需 API key 的本地 host runner（Codex / Trae / Claude / 任意无头 CLI）。.
generate-component
Generate Angular standalone component with tests.
pack-repo
Pack la codebase en un fichier AI-friendly (Repomix wrapper + fallback shell). Token counting inclus.
deploy
Build, test, deploy with staged rollout.
simplify
Reduce complexity without changing behavior — code simplification.
coograph-verify
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.