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 skills/sandbox-quantum/switch/configurenpx skills add sandbox-quantum/switch --skill configuregit clone --depth 1 https://github.com/sandbox-quantum/switchWhat 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 | $0.00061 | $0.11151 |
| Opus 5 | $0.00030 | $0.05575 |
| Sonnet 5 | $0.00012 | $0.02230 |
| Haiku 4.5 | $0.00006 | $0.01115 |
Grade D, and why
configure scanned grade D with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Check the environment for `SWITCH_REGISTRATION_TOKEN` (`printenv SWITCH_REGISTRATION_TOKEN`). If unset, ask the user to paste it and tell them Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ".switch/agents/$NAME.json" Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> `~/.claude/settings.json`. The plugin's declaration is the single definition of Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -w '\n%{http_code}\n' --max-time 10 "$ENDPOINT/health" 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.
- 3d ago First seen · 897 lines · 61 tokens per session scan D a883a3aabe1b
configure is a skill published in the GitHub repository sandbox-quantum/switch (446 stars, last pushed 4d ago), with no licence file. It adds 61 tokens to every session and 11,151 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 4 findings (harvests environment variables, asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-quality
Python coding patterns, idioms, and quality standards for claude-code-discord-bridge development.
test-guide
Testing patterns for claude-code-discord-bridge — pytest, async testing, mocking Discord objects, TDD workflow.
release
Skill "release" from ebibibi/ebi-agent-chat-relay, covering ccdb リリース手順, バージョン体系, 手動リリース手順（「v1.4.0としてリリースして」）, step 1: リポジトリに入る and step 2: ブランチを作る.
security-audit
Security checklist specific to claude-code-discord-bridge — subprocess injection, env leaks, input validation.
add-cog
Step-by-step guide to add a new discord.py Cog to the framework.
verify
Run full verification pipeline (lint, format, test, security) before committing.