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.
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote 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/cdeust/ai-architect-mcp-codebase/spawn)<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/spawn"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/spawn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/spawn"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/spawn.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00146 |
| Opus 5.5 | $0.00000 | $0.00058 |
| Sonnet 5.5 | $0.00000 | $0.00029 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
spawn 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 1mo 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.
What it actually says
Spawn Agent in Worktree
Spawn an agent as a standalone Claude Code session in an isolated git worktree.
Instructions
-
Parse arguments: the first word is the agent name, the rest is the task description. Example:
/agent-spawn engineer Fix the auth bug in login.py -
Validate the agent exists by checking
agents/<name>.mdoragents/genius/<name>.md. -
Run:
scripts/spawn-agent.sh <agent-name> "<task>" -
Report the worktree path and branch name to the user.
-
If no task is provided, spawn in interactive REPL mode (no
-pflag).
$ARGUMENTS
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.
- 1mo ago First seen · 19 lines · 0 tokens per session scan A 48058a5a3a07
spawn is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 146 tokens. 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 2026-08-31.
Other commands, from other repositories
converge
Run an unattended review→fix→re-review loop on the current branch until the reviewer has no findings at or above Medium, then push once. Findings stay in a local scratch file and are never posted to GitHub. Stops early on oscillation, a red test suite, or a 4-review cap.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
doctor
Read-only preflight check of runtime dependencies (gh, git, jq, rimba, claude, python3) plus gh auth status and .claude/cache/ repo hygiene. Prints a green/red table; never modifies state. Exit 0 regardless of findings; exits 1 only if the swe-workbench-doctor command is not on PATH.
implement
Drive a feature implementation end-to-end from a ticket or spec — branch, plan, build, verify, review, deliver.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
sync
Bring the current branch up to date with the default branch — delegates the mechanical merge/rebase to rimba (or git), then walks through any conflicts file-by-file with a recommended resolution before applying. Never auto-pushes. Always fetches origin's default branch before comparing. Pass --rebase to rebase instead…