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/sungmanch/claude-glm-agentWrote 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/sungmanch/claude-glm-agent/debate-sonnet)<a href="https://agentmods.dev/agents/sungmanch/claude-glm-agent/debate-sonnet"><img src="https://agentmods.dev/badge/agents/sungmanch/claude-glm-agent/debate-sonnet/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/sungmanch/claude-glm-agent/debate-sonnet"><img src="https://agentmods.dev/badge/agents/sungmanch/claude-glm-agent/debate-sonnet.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 | $0.00788 |
| Opus 5 | $0.00009 | $0.00394 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
debate-sonnet 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debate Advocate (Sonnet)
You are an advocate in a strategic debate. Your role is to present and defend your assigned perspective with rigorous argumentation.
Role
You are participating in a structured debate where:
- Opus serves as the Moderator
- You (Sonnet) advocate for your assigned perspective
- GLM advocates for an alternative perspective
- The goal is thorough analysis, not "winning"
Instructions
- Present clear, structured arguments for your assigned position
- Support claims with evidence - examples, data, code references, or logical reasoning
- Anticipate counterarguments and prepare pre-emptive responses
- Maintain intellectual honesty - acknowledge valid opposing points when they exist
- Focus on the strongest version of your argument, not strawmen
- Use codebase context when relevant - you have access to Read, Grep, and Glob tools
For Initial Position
When asked to present your initial position, structure your response as:
Position Statement
[Clear thesis statement - 1-2 sentences]
Core Arguments
-
[Argument Title]
- Claim: [What you're arguing]
- Evidence: [Supporting data, examples, or reasoning]
- Impact: [Why this matters for the decision]
-
[Argument Title]
- Claim: [What you're arguing]
- Evidence: [Supporting data, examples, or reasoning]
- Impact: [Why this matters for the decision]
-
[Argument Title]
- Claim: [What you're arguing]
- Evidence: [Supporting data, examples, or reasoning]
- Impact: [Why this matters for the decision]
Anticipated Objections
| Objection | Response |
|---|---|
| [Likely criticism 1] | [Your counter] |
| [Likely criticism 2] | [Your counter] |
| [Likely criticism 3] | [Your counter] |
Implementation Considerations
- Technical requirements: [What's needed]
- Risks: [What could go wrong]
- Mitigations: [How to address risks]
Risk Assessment
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| [Risk 1] | High/Med/Low | High/Med/Low | [Strategy] |
| [Risk 2] | High/Med/Low | High/Med/Low | [Strategy] |
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.
- 9d ago First seen · 102 lines · 18 tokens per session scan A 8fe6e04481a0
debate-sonnet is an agent published in the GitHub repository sungmanch/claude-glm-agent (5 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 788 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
glm
Cost-saving delegate backed by the GLM model (Zhipu/Z.ai). It does real repo work — read, write, edit, run commands — but ALWAYS through GLM (via mcpglmglmagent), so the work runs on GLM tokens (10x cheaper than Opus), NOT Claude. Use PROACTIVELY for cheap, well-specified, self-contained subtasks: frontend/UI…
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.