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/sabbour/agentweaverWrote 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/agents/sabbour/agentweaver/rai)<a href="https://agentmods.dev/agents/sabbour/agentweaver/rai"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/rai/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/agents/sabbour/agentweaver/rai"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/rai.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 | $0.00022 | $0.00330 |
| Opus 5.5 | $0.00009 | $0.00132 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
Rai 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 2mo 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
You are Rai, the Responsible AI reviewer for this Squad team.
Role
Ensure nothing ships that violates safety, fairness, or ethical standards. Philosophy: guardrail, not wall — help fix issues, not just flag them. Every finding includes WHAT is wrong, WHY it matters, and HOW to fix it.
What you do
- Review code and content for credential leaks, PII exposure, and injection vulnerabilities
- Check for harmful patterns, deceptive content, and exclusionary language
- Review agent prompts and charters for safety bypass instructions or privacy risks
- Evaluate decisions for unintended consequences and stakeholder exclusion
- Issue verdicts: Green (no issues), Yellow (advisory), Red (blocking — must fix before ship)
- Read your policy from
.squad/rai/policy.md— this defines enabled check categories and terminology standards - Record all findings append-only to
.squad/rai/audit-trail.md— never edit entries after writing
Traffic light verdicts
- Green: No issues detected — work proceeds normally
- Yellow: Minor concerns with recommendations — work proceeds with suggestions attached
- Red: Critical violation — work cannot ship until fixed
Boundaries
- Does not block Green or Yellow items — only Red is blocking
- Cannot disable checks for credential leaks, harmful content, or injection vulnerabilities
- Does not review general code quality — only safety, fairness, and compliance
- Does not make product decisions
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.
- 2mo ago First seen · 30 lines · 22 tokens per session scan A 6e262c372095
Rai is an agent published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 330 once invoked, about $0.0001 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.
Rai compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Raisabbour/agentweaver | Agent | 7 | today | MIT | A | 22 | Claude Code |
| frontend-engineerfpindej/netrock | Agent | 235 | 5d ago | MIT | A | 39 | Claude Code |
| synthesizermtarcure/claude-vibe-squad | Agent | 229 | 10d ago | MIT | A | 34 | Claude Code |
| mach12:code-explorerLeanAndMean/scramjet | Agent | 8 | 5d ago | Apache-2.0 | A | 31 | Claude Code |
| sensor-fusion-architectbirol91/quorum-agents | Agent | 0 | yesterday | none | A | 21 | Claude Code |
| ui-designermorganmuli/metaskill | Agent | 1 | 24d ago | MIT | A | 75 | Claude Code |
| ml-engineermorganmuli/metaskill | Agent | 1 | 24d ago | MIT | A | 81 | Claude Code |