System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.
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 asgeirtj/system_prompts_leaks --skill zcode-configuration-guidegit clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksWrote 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/asgeirtj/system_prompts_leaks/zcode-configuration-guide)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/zcode-configuration-guide"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/zcode-configuration-guide/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/skills/asgeirtj/system_prompts_leaks/zcode-configuration-guide"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/zcode-configuration-guide.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 | $0.00123 | $0.02368 |
| Opus 5.5 | $0.00049 | $0.00947 |
| Sonnet 5.5 | $0.00025 | $0.00474 |
| Haiku 4.5 | $0.00012 | $0.00237 |
Grade A, and why
zcode-configuration-guide 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZCode Configuration Guide
ZCode supports five types of extension resources, plus AGENTS.md instruction files. This skill is the map: it tells you where each resource is configured and how conflicts are resolved. For "something is not working, how do I fix it," follow the routing to the diagnosing-* skills at the end.
How things are configured
There are two ways to work with configuration in the ZCode client, and this plugin serves both:
- A person manages resources through the client's graphical interface — Settings → Plugin Management, Settings → Skills, Settings → Subagents, Settings → MCP, and the
/menu in the input box. - An agent repairs configuration by reading and editing the underlying files directly with its file tools. The locations and rules below are what an agent uses to find the right file and field.
Scopes and the main configuration files
- User scope — lives under your home directory and applies to every workspace.
- Workspace scope — lives inside a repository and applies only to that project; can be shared with a team through version control.
- User configuration file:
~/.zcode/cli/config.json. Holds MCP servers, hooks, plugin enable/disable state, and skill/command disable overrides. - Workspace configuration file:
<repo>/.zcode/config.json(or<repo>/zcode.json). - User instruction file:
~/.zcode/AGENTS.md. Applies as default instructions for every workspace. - Workspace instruction file:
<repo>/AGENTS.md. Applies only to that project; the current workspace path is searched upward until the project root.
The five resources at a glance
| Resource | Form | User scope | Workspace scope | Conflict rule |
|---|---|---|---|---|
| Skills | Directory + SKILL.md |
~/.zcode/skills/, ~/.agents/skills/ |
<repo>/.zcode/skills/, <repo>/.agents/skills/ |
Identity is the file path; on load the first same-named skill wins (user scope has priority) |
| Commands | .md file |
~/.zcode/commands/, ~/.agents/commands/ |
<repo>/.zcode/commands/, <repo>/.agents/commands/ |
Deduplicated by normalized command name; first match wins (user scope overrides workspace), the loser is ignored |
| MCP | JSON object | ~/.zcode/cli/config.json → mcp.servers (fallback ~/.agents/mcp.json → mcpServers) |
<repo>/.zcode/config.json → mcp.servers (fallback <repo>/.agents/mcp.json → mcpServers) |
User overrides workspace for a same-named server; workspace-scoped servers are trusted and auto-connected by default, same as user-scoped |
| Hooks | hooks.json / config object |
~/.zcode/cli/config.json → hooks |
<repo>/.zcode/config.json → hooks |
Configuration-file hooks require hooks.enabled: true; plugin hooks are appended |
| Plugins | Directory + plugin.json |
Installed from a marketplace; enable/disable state stored in ~/.zcode/cli/config.json |
— | A plugin contributes skills, commands, hooks, MCP servers, and agents |
| Instructions | AGENTS.md file |
~/.zcode/AGENTS.md |
<repo>/AGENTS.md |
User default instructions load first, then workspace instructions load later so the workspace can narrow or override broad defaults |
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.
- 2d ago First seen · 100 lines · 123 tokens per session scan A 93b627b6922c
zcode-configuration-guide is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,207 stars, last pushed today), licensed CC0-1.0. It adds 123 tokens to every session and 2,368 once invoked, about $0.0005 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 2026-10-24.
Other skills, from other repositories
ast-grep
AST-aware structural code search and rewrite via ast-grep.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
hermes-s6-container-supervision
Modify or debug s6 services in the Hermes Docker image.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.