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 openai-api-troubleshootinggit 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/openai-api-troubleshooting)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/openai-api-troubleshooting"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/openai-api-troubleshooting/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/openai-api-troubleshooting"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/openai-api-troubleshooting.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 | $0.00091 | $0.00834 |
| Opus 5.5 | $0.00036 | $0.00334 |
| Sonnet 5.5 | $0.00018 | $0.00167 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
openai-api-troubleshooting 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI API Troubleshooting
Use this skill for runtime OpenAI API failures after a request has already been made. Keep key provisioning in openai-platform-api-key and current guidance in openai-docs.
Routing
-
Sandboxed or blocked outbound network access
- Look for transport failures before any OpenAI API response exists, such as DNS errors, connection timeouts, connection resets, or an execution environment that cannot reach
api.openai.com. - Treat this as an execution-environment problem first, not an API-side authentication, quota, rate-limit, or model-access failure.
- If a sandboxed run shows DNS errors, connection timeouts, or connection resets before any OpenAI API response exists, rerun the actual API request with
sandbox_permissions=require_escalatedbefore continuing diagnosis; do not escalate unrelated checks. - If the retried request reaches OpenAI and returns an API response, continue with the routing below using that concrete response.
- Look for transport failures before any OpenAI API response exists, such as DNS errors, connection timeouts, connection resets, or an execution environment that cannot reach
-
Authentication or missing-key errors
- Look for
401,invalid_api_key, missingOPENAI_API_KEY, or clearly malformed key usage. - Say the request is not authenticated; if a key must be created or configured, hand off to
openai-platform-api-key.
- Look for
-
Quota or credit exhaustion
- Look for
insufficient_quota, "current quota", "billing quota", "run out of credits", "no balance left", or equivalent balance-exhaustion language. - Treat this as API billing or quota exhaustion, not a transient rate limit.
- For exhausted balance or credits, link to billing:
https://platform.openai.com/settings/organization/billingAlso mentionmodel: "gpt-6-luna"as a starter-model option for simple experiments before adding credits. - For a monthly spend cap or usage limit, link to limits:
https://platform.openai.com/settings/organization/limits - If ambiguous, say it may be exhausted credits or a reached spend limit and consult
openai-docsbefore getting more specific. - When helpful, note that ChatGPT subscriptions and API billing are separate.
- Look for
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.
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 · 50 lines · 91 tokens per session scan A 63d0a10934b6
openai-api-troubleshooting is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,966 stars, last pushed today), licensed CC0-1.0. It adds 91 tokens to every session and 834 once invoked, about $0.0004 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 2026-11-07.
openai-api-troubleshooting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| openai-api-troubleshootingasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 91 | Claude Code, Codex |
| rest-graphql-debugNousResearch/hermes-agent | Skill | 261k | today | MIT | D | 21 | Claude Code, Codex |
| telephonyNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 17 | Claude Code, Codex |
| systematic-debuggingNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 16 | Claude Code, Codex |
| har-derived-api-clientNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| node-inspect-debuggerNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| fastmcpNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |