A prompt-writing guide for tasks sent to GLM models, including GLM 5.2. It supports prompts written for direct user use and prompts passed to an autonomous subagent.

Use it to draft or refine a GLM prompt, prepare a GLM subagent task, or select the appropriate prompt format.

It helps adapt instructions to GLM's known failure patterns and clarifies which prompt mode is needed.

glm-prompt — Skill for Claude Code and Codex by knopki/agent-skills

Install

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.

Any agent

npx skills add knopki/agent-skills --skill glm-prompt

Clone the repo

git clone --depth 1 https://github.com/knopki/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/knopki/agent-skills/glm-prompt/github.svg)](https://agentmods.dev/skills/knopki/agent-skills/glm-prompt)

Your own site

<a href="https://agentmods.dev/skills/knopki/agent-skills/glm-prompt"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/glm-prompt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/knopki/agent-skills/glm-prompt"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/glm-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00083	$0.03655
Opus 5.5	$0.00033	$0.01462
Sonnet 5.5	$0.00017	$0.00731
Haiku 4.5	$0.00008	$0.00365

Measured 2mo ago against content hash 8105473e99c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glm-prompt scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- For a fix: `curl … ; expect { "ok": true }`

skills/glm-prompt/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLM Prompt Skill

Overview

Build prompts that play to GLM 5.2's strengths and avoid its known failure modes.

Two operating modes:

Interactive mode (prompt is for the end user in this session): run the interrogation in §3 — collect the info the user has, then fill the template.
Subagent / autonomous mode (prompt will be sent to a GLM subagent or a fresh GLM session): decide the content yourself from available context — do NOT interrogate the user. Use §4.

Decide the mode from how the request is phrased:

"write me a prompt for GLM to do X" / "I want to prompt GLM to…" → interactive.
"launch a subagent to do X on GLM" / "prepare a prompt for the GLM agent" / the prompt is a parameter you pass to a Task/Agent call → subagent mode.

If the intent is ambiguous, ask one clarifying question: "Is this prompt for you to send into a GLM session yourself, or should I write it as a subagent/Agent task prompt?" — then proceed.

When to Use

Trigger this skill whenever you are about to produce a prompt whose target runtime is a GLM model. Concretely:

The user asks you to "write / draft / compose a prompt for GLM", "make a prompt for GLM", "format this task for GLM".
You are composing the prompt: argument of a task() / subagent call that will run on a GLM model.
You are translating a vague user request into a clean GLM task spec.

Do not trigger this skill for non-GLM models.

1) The format — Goal, Context, Constraints, Done

GLM is trained on structured long-horizon tasks. Four sections are enough for it to plan a trajectory. Use this exact structure:

### Goal

[1–2 sentences: what to do]

### Context

- Files: [paths, with line ranges when known]
- Current state: [how it is now; if a bug — what's wrong]
- Why: [the reason this is being done]

### Constraints

- Do not touch: [boundaries — what cannot change]
- Style: [language, code style, architectural rules]
- Versions: [dependencies, API versions]

### Done

- Validation: [command or scenario — how to be sure]
- Result format: [what to return — file, summary, diff]

Read the full file on GitHub · 371 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 130 B

Changes

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 · 371 lines · 83 tokens per session scan A 8105473e99c3

Subscribe to this mod's changes

glm-prompt is a skill published in the GitHub repository knopki/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 3,655 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Prompting

glm-prompt next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
glm-promptknopki/agent-skills	Skill	2	3d ago	MIT	A	83	Claude Code, Codex
llm-app-patternsdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	54	Claude Code, Codex
prompt-engineerJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	93	Claude Code
prompt-optimizationlangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	105	Claude Code, Codex
omh-model-optimizationrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	84	Claude Code, Codex
ideogram4digitalsamba/claude-code-video-toolkit	Skill	2.5k	yesterday	MIT	A	99	Claude Code
prompt-library-for-startupsaws/agent-toolkit-for-aws	Skill	3.4k	yesterday	Apache-2.0	A	228	Claude Code

glm-prompt