asgeirtj/system_prompts_leaks

Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

About the project

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.

65kStars on the repository
53Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
CC0-1.0Licence, which decides whether bodies are shown

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared…

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 125 tokens original CC0-1.0

artifact-design

02

asgeirtj/system_prompts_leaks

Skill Claude Code

Design guidance and fundamentals for Artifacts.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 11 tokens original CC0-1.0

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 45 tokens original CC0-1.0

batch

04

asgeirtj/system_prompts_leaks

Skill Claude Code

Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 30 tokens original CC0-1.0

claude-in-chrome

05

asgeirtj/system_prompts_leaks

Skill Claude Code

Automates your Chrome browser to interact with web pages - clicking elements, filling forms, capturing screenshots, reading console logs, and navigating sites. Opens pages in new tabs within your existing Chrome session. Requires site-level permissions before executing (configured in the extension).

not rated 65k +206 yesterday A ✓ AI review Snyk: warnSkillSpector: warn 57 tokens original CC0-1.0

code-review

06

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Review the current diff, or a PR number/branch/path target, for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud); with no level…

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 0 tokens original CC0-1.0

Data Visualization

07

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Produce a chart, graph, dashboard, or any data visualization that reads as one system - elegant, accessible, and consistent in light and dark - BRAND-NEUTRAL, shipping a placeholder palette to swap for your own. Read this BEFORE generating ANY chart (bar, line, area, heatmap, scatter, sparkline, donut), choosing chart…

not rated 65k +206 yesterday A ✓ AI review SkillSpector: pass 232 tokens original CC0-1.0

debug

08

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Enable debug logging for this session and help diagnose issues.

not rated 65k +206 yesterday A ✓ AI review SkillSpector: warn 12 tokens original CC0-1.0

deep-research

09

asgeirtj/system_prompts_leaks

Skill Claude Code

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

not rated 65k +206 yesterday A ✓ AI review Snyk: warnSkillSpector: pass 28 tokens original CC0-1.0

design-sync

10

asgeirtj/system_prompts_leaks

Skill Claude Code

Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says "sync my design system to Claude Design".

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 56 tokens original CC0-1.0

non-storybook

11

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex needs its repo

No Storybook - the component list comes from the package's shipped .d.ts exports, and there is no reference render to verify against. Preview quality therefore comes from two layers: the converter ships every component fully functional (bundle + .d.ts + .prompt.md) with an honest floor card, and rich previews are…

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 0 tokens original CC0-1.0

storybook

12

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex needs its repo

Storybook is the fidelity oracle, not the runtime. The converter bundles the package's compiled dist/ into dsbundle.js - the same bundle the claude.ai/design agent builds with - and generates each preview by compiling the story source module itself (hooks, fixtures, local helpers - the whole closure comes along), with…

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 0 tokens original CC0-1.0

design

13

asgeirtj/system_prompts_leaks

Skill Claude Code

Create a design canvas - a multi-artboard visual design published as an Artifact that runs Claude Design's canvas editor (an early preview of Claude Design inside Claude Code). You DRAFT the design as .dc.html artboards laid out on one pan/zoom canvas; where saving is enabled for the user's account they refine every…

not rated 65k +206 yesterday A ✓ AI review Snyk: warnSkillSpector: warn 224 tokens original CC0-1.0

doctor

14

asgeirtj/system_prompts_leaks

Skill Claude Code

Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the claude doctor terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused…

not rated 65k +206 yesterday A ✓ AI review SkillSpector: warn 214 tokens original CC0-1.0

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.

not rated 65k +206 yesterday B ✓ AI review SkillSpector: warn 38 tokens original CC0-1.0

init

16

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Initialize a new CLAUDE.md file with codebase documentation.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 14 tokens original CC0-1.0

keybindings-help

17

asgeirtj/system_prompts_leaks

Skill Claude Code

Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 57 tokens original CC0-1.0

loop

18

asgeirtj/system_prompts_leaks

Skill Claude Code

Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.

not rated 65k +206 yesterday A ✓ AI review Snyk: warnSkillSpector: pass 36 tokens original CC0-1.0

run-skill-generator

19

asgeirtj/system_prompts_leaks

Skill Claude Code

Author or improve the run- skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 65 tokens original CC0-1.0

run

20

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI…

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 80 tokens original CC0-1.0

schedule

21

asgeirtj/system_prompts_leaks

Skill Claude Code

Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 24 tokens original CC0-1.0

security-review

22

asgeirtj/system_prompts_leaks

Skill Claude Code

Complete a security review of the pending changes on the current branch.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: warn 15 tokens original CC0-1.0

simplify

23

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.

not rated 65k +206 yesterday A ✓ AI review Snyk: passSkillSpector: pass 42 tokens original CC0-1.0

verify

24

asgeirtj/system_prompts_leaks

Skill Claude Code

Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches…

not rated 65k +206 yesterday A ✓ AI review SkillSpector: warn 95 tokens original CC0-1.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: