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 chrome-devtoolsgit 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/chrome-devtools)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/chrome-devtools"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/chrome-devtools/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/chrome-devtools"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/chrome-devtools.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 | $0.00055 | $0.00996 |
| Opus 5.5 | $0.00022 | $0.00398 |
| Sonnet 5.5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
chrome-devtools 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 today.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- chrome-devtools — 95% identical, 10 lines differ
- chrome-devtools — 95% identical, 13 lines differ
- brave-devtools — 89% identical, 22 lines differ
- chrome-devtools — 88% identical, 18 lines differ
- chrome-devtools — 88% identical, 13 lines differ
- chrome-devtools — 88% identical, 18 lines differ
- chrome-devtools — 84% identical, 22 lines differ
- chrome-devtools — 83% identical, 38 lines differ
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Concepts
Browser lifecycle: Browser starts automatically on first tool call using a persistent Chrome profile. Configure via CLI args in the MCP server configuration: npx chrome-devtools-mcp@latest --help.
Addional tooling can be enabled by providing the following flags:
- For extension tooling, use the
--categoryExtensionsflag. - For memory tooling, use the
--memoryDebuggingflag.
Page targeting: Page-scoped tools require a pageId parameter to target a specific page. Use list_pages to see available pages and their IDs (e.g. pageId: 1), or use the ID returned when creating a page with new_page.
Note: For evaluate_script, pageId is required when targeting pages. However, when --categoryExtensions is enabled, pageId is optional so you can pass serviceWorkerId instead to evaluate inside an extension background service worker.
Element interaction: Use take_snapshot to get page structure with element uids. Each element has a unique uid for interaction. If an element isn't found, take a fresh snapshot - the element may have been removed or the page changed.
Workflow Patterns
Before interacting with a page
- Navigate:
navigate_pageornew_page - Wait:
wait_forto ensure content is loaded if you know what you look for. - Snapshot:
take_snapshotwithpageIdto understand page structure - Interact: Use element
uids from snapshot forclick,fill, etc., passing the correspondingpageId.
Efficient data retrieval
- Use
filePathparameter for large outputs (screenshots, snapshots, traces) - Use pagination (
pageIdx,pageSize) and filtering (types) to minimize data - Set
includeSnapshot: falseon input actions unless you need updated page state
Tool selection
- Automation/interaction:
take_snapshot(text-based, faster, better for automation) - Visual inspection:
take_screenshot(when user needs to see visual state) - CSS & Styling inspection: Use
get_css_stylesto inspect matched rules, cascade, and CSS variables. Treat the output as authoritative and complete. - Additional details: Use
evaluate_scriptfor runtime DOM/JS data not available viaget_css_stylesortake_snapshot.
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.
- today First seen · 75 lines · 55 tokens per session scan A 8b217ff6a941
chrome-devtools is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,425 stars, last pushed yesterday), licensed CC0-1.0. It adds 55 tokens to every session and 996 once invoked, about $0.0002 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 2026-10-30.
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.
har-derived-api-client
Record a site's XHR into a HAR, derive an HTTP client.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
scrapling
Scrape sites with stealth browsing and Cloudflare bypass.