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 debuggit 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/debug)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/debug"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/debug/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/debug"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Agent Snooping · line 35 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 36 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 37 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00012 | $0.00374 |
| Opus 5 | $0.00006 | $0.00187 |
| Sonnet 5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
debug 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 9d 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.
What it actually says
Debug Skill
Help the user debug an issue they're encountering in this current Claude Code session.
Debug Logging Just Enabled
Debug logging was OFF for this session until now. Nothing prior to this /debug invocation was captured.
Tell the user that debug logging is now active at {debug_log_path}, ask them to reproduce the issue, then re-read the log. If they can't reproduce, they can also restart with claude --debug to capture logs from startup.
Session Debug Log
The debug log for the current session is at: {debug_log_path}
No log file exists yet.
For additional context, grep for [ERROR] and [WARN] lines across the full file.
Daemon
No daemon lock or status file found — the background daemon does not appear to be running. If the issue involves background sessions or claude agents, the daemon log (if any) is at {user_home}/.claude/daemon.log.
Issue Description
The user did not describe a specific issue. Read the debug log and summarize any errors, warnings, or notable issues.
Settings
Remember that settings are in:
- user - {user_home}/.claude/settings.json
- project - {working_directory}/.claude/settings.json
- local - {working_directory}/.claude/settings.local.json
Instructions
- Review the user's issue description
- The last 20 lines show the debug file format. Look for [ERROR] and [WARN] entries, stack traces, and failure patterns across the file
- Consider launching the claude-code-guide subagent to understand the relevant Claude Code features
- Explain what you found in plain language
- Suggest concrete fixes or next steps
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.
- 9d ago First seen · 46 lines · 12 tokens per session scan B b5c5f4ecc88e
debug is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,387 stars, last pushed yesterday), licensed CC0-1.0. It adds 12 tokens to every session and 374 once invoked, about $0.0001 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
hermes-s6-container-supervision
Modify or debug s6 services in the Hermes Docker image.
ast-grep
AST-aware structural code search and rewrite via ast-grep.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
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.