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 skills add tu11aa/squadrant --skill add-pick-crew-rulegit clone --depth 1 https://github.com/tu11aa/squadrantWrote 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/skills/tu11aa/squadrant/add-pick-crew-rule)<a href="https://agentmods.dev/skills/tu11aa/squadrant/add-pick-crew-rule"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/add-pick-crew-rule/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/skills/tu11aa/squadrant/add-pick-crew-rule"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/add-pick-crew-rule.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 | $0.00043 | $0.01296 |
| Opus 5.5 | $0.00017 | $0.00518 |
| Sonnet 5.5 | $0.00009 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
add-pick-crew-rule 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Crew Routing Rules
Crew routing rules live in defaults.crewRouting.rules inside ~/.config/squadrant/config.json.
Each rule has the shape:
{
"tier": "<label>", // human label, e.g. "extreme" / "hard" / "daily"
"match": "<regex>", // case-insensitive regex tested against the task text
"agent": "claude|codex|gemini|opencode",
"model": "opus|sonnet|flash|<literal upstream id>", // a squadrant alias or a literal
"backend": "native|direct|proxy" // optional; claude-only for direct/proxy
}
Rules are evaluated in order; the first match wins.
direct/proxy are claude-only; native is valid for any agent:
native(default) — the CLI's own auth; no router needed.direct— point Claude atdefaults.router.baseUrldirectly (env injection lands in U3).proxy— point Claude at the squadrant loopback shim (env injection lands in U3).
A rule with backend: "direct" or "proxy" requires defaults.router to be configured;
otherwise the spawn fails with a hard error and squadrant config check flags it.
model may be either a squadrant alias (defined in defaults.router.models) or a literal
upstream id. An alias expands per agent — e.g. flash →
deepseek-v4.1-flash for claude, opencode-go/deepseek-v4.1-flash for opencode. A value that is
not a defined alias is used verbatim, so existing configs keep working.
Adding a rule
-
Read the current config:
cat ~/.config/squadrant/config.json -
Identify the
defaults.crewRouting.rulesarray. If it is absent, add it. -
Build the new rule object. Validate:
tieris a non-empty stringmatchis a valid regex (test it mentally against a sample task string)agentis one ofclaude,codex,gemini,opencodebackend(optional) is one ofnative,direct,proxy;direct/proxyare claude-only and requiredefaults.router(only matters whenagentisclaude)modelapplies to claude/opencode (codex does not consume it): may be a squadrant alias (seedefaults.router.models) or a literal upstream id; aliases expand per agent
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 Changed · +17 lines 641d65211f32
- 2mo ago First seen · 89 lines · 43 tokens per session scan A b6ec09de2c77
add-pick-crew-rule is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,296 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
add-pick-crew-rule compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-pick-crew-ruletu11aa/squadrant | Skill | 2 | yesterday | MIT | A | 43 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |