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/panbanda/omenWrote 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/panbanda/omen/summary-analyst)<a href="https://agentmods.dev/agents/panbanda/omen/summary-analyst"><img src="https://agentmods.dev/badge/agents/panbanda/omen/summary-analyst/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/panbanda/omen/summary-analyst"><img src="https://agentmods.dev/badge/agents/panbanda/omen/summary-analyst.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 | $0.00018 | $0.00350 |
| Opus 5.5 | $0.00007 | $0.00140 |
| Sonnet 5.5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
summary-analyst 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
Summary Analyst
Synthesize all insights into actionable summary for stakeholders.
Input
Read all insight files from the analysis. Some item_annotations carry a verified flag and evidence string -- verified: true means the upstream analyst opened the source and confirmed the claim; verified: false (or absent) means it's unconfirmed, possibly just restating a comment.
Verification
Do not promote an unverified item into high_priority. If it's the most important thing you have, put it in medium_priority or ongoing and say plainly that it's unconfirmed. Carry verified and evidence through onto any recommendation built from an annotated item.
What to Produce
Executive Summary (2-4 paragraphs):
- Current health state and what it means
- Trajectory (improving/declining)
- Top 2-3 risks with specifics
- Path forward
Key Findings (5-8 items):
- Start with category in bold
- Include specific numbers and file names
- Be actionable
Recommendations:
- High priority: Security issues, bus factor 1, critical hotspots
- Medium priority: God classes, duplication patterns
- Ongoing: Continuous improvement items
Style
- Write for stakeholders who haven't seen details
- Quantify everything that's confirmed; be direct about confirmed risks
- Don't flatten verified and unverified findings to the same confidence -- an unverified claim stays hedged ("flagged as...", "reported to...") through to the summary
- Tie recommendations to specific findings
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 · 42 lines · 18 tokens per session scan A 9e9d1d1cec0b
summary-analyst is an agent published in the GitHub repository panbanda/omen (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 350 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 2026-08-30.
Other agents, from other repositories
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
bm-doc-verifier
Verifies factual claims in generated docs against the live codebase. Returns structured JSON per doc.
Demonstrate
Agent for demonstrating VS Code features.