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/joelhooks/swarm-tools/inboxgit clone --depth 1 https://github.com/joelhooks/swarm-toolsWhat 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 | $0.00125 |
| Opus 5 | $0.00005 | $0.00063 |
| Sonnet 5 | $0.00002 | $0.00025 |
| Haiku 4.5 | $0.00001 | $0.00013 |
Grade A, and why
inbox 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 20 lines · 9 tokens per session scan A cdab0bdfccb1
inbox is a command published in the GitHub repository joelhooks/swarm-tools (733 stars, last pushed 1mo ago), with no licence file. It adds 9 tokens to every session and 125 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
distill
Distill hot-tier model observations into the committed capability cards and the SKILL.md rankings block.
dag-routing
Build a Workflow DAG that delegates each node's work to a non-Claude model (GPT/Grok/Kimi/GLM/MiniMax/Qwen) via the shims.
fusion-status
Health-check the Fusion setup - installed, loaded, and enforcing.
fusion-setup
Configure or reconfigure the opencode Fusion agent team.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.