GLM-5 is an open-weights large language model designed for coding and long-running agent tasks. It is used by developers building software agents and other applications that need model-based reasoning.
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 zai-org/GLM-5 --skill glm-master-skillgit clone --depth 1 https://github.com/zai-org/GLM-5Wrote 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/zai-org/glm-5/glm-master-skill)<a href="https://agentmods.dev/skills/zai-org/glm-5/glm-master-skill"><img src="https://agentmods.dev/badge/skills/zai-org/glm-5/glm-master-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 69 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 75 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 76 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 77 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 83 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 142 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 120 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00045 | $0.01723 |
| Opus 5 | $0.00023 | $0.00861 |
| Sonnet 5 | $0.00009 | $0.00345 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
glm-master-skill 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 8d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GLM Master Skill (Guide Only) / GLM 技能总览（仅指南）
This is a documentation-only master skill.
- ✅ It introduces available GLM skills.
- ✅ It provides official install links and commands.
- ❌ It does not run any local scripts.
- ❌ It does not use subprocess.
本 Skill 只做导航与安装说明，不执行任何本地脚本。
Official Skills Catalog / 官方技能目录
GLM-OCR
| Skill | Purpose | Link |
|---|---|---|
glmocr |
General OCR (text extraction) | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr |
glmocr-table |
Table extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-table |
glmocr-formula |
Formula extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-formula |
glmocr-handwriting |
Handwriting OCR | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-handwriting |
sdk |
GLM-OCR SDK guidance | https://github.com/zai-org/GLM-OCR/tree/main/skills/sdk |
GLM-Image
| Skill | Purpose | Link |
|---|---|---|
glm-image-gen |
Text-to-image generation | https://github.com/zai-org/GLM-Image/tree/main/skills/glm-image-gen |
GLM-V
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.
- 8d ago First seen · 181 lines · 45 tokens per session scan A a31dd9601eda
glm-master-skill is a skill published in the GitHub repository zai-org/GLM-5 (7,153 stars, last pushed 6d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,723 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
Claude Code
Guides operator-owned delegation to Claude Code when repo work benefits from a second coding lane or an interactive code agent.
Codex
Guides operator-owned delegation to Codex when the task fits a bounded coding lane, review pass, or worktree-isolated implementation track.
OpenCode
Frames OpenCode as an operator-controlled coding lane for bounded implementation or review work inside a real repository.
coding-assistant
Help users write, review, and debug code.
metamorphic-testing
Test systems with no reliable oracle using metamorphic relations — equivalence-preserving input transforms whose outputs must agree, with concrete relations for LLM/NLP stability.
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …