# togg53192-cmd/jailbreaks

> A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model behavior.

- Magnitude: 5.6 out of 10 — Breakout
- Stars: 4,954 total · +104 stars measured 2026-10-27, 11:41–13:22 UTC, ≈ 305 by evening
- Star trust: star growth looks organic
- Category: Language models · Created: 2026-06-18 · Last push: 2026-10-25
- GitHub: https://github.com/togg53192-cmd/jailbreaks · Page: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks

## Useful for

- Copy a system prompt from a file into a client's custom instructions or API field
- Drop AGENTS.md into a repository root to configure a coding agent
- Build an Ollama model with ollama create from the supplied Modelfile

## Why it’s here

- Star-counter measurements on 2026-10-27 (UTC), 11:41–13:22: 4850 → 4954 stars (+104). This is the change over that interval.
- Estimated end-of-day forecast: about +305 stars, using observed gains and the previous day.
- Over the last two days the pace is 8.2× that of the previous week and a half.
- GitHub Trending today: #10, +890 stars.
- About 80 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 784
- Issues and pull requests: 21
- Watchers: 64
- Average over the last week: 238 per day
- Usual pace: 72 per day
- Stars in the last hour (measured): 59

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-28 … 2026-10-27: 428, 231, 110, 85, 83, 63, 38, 67, 72, 38, 41, 43, 56, 61, 52, 59, 69, 54, 51, 68, 65, 67, 96, 68, 81, 92, 70, 192, 858, 104

## Spotted in now

- GitHub Trending today: #10, +890 stars

## Similar by description

1. **routerhubSI/glm-5.3-abliterated** — 1.9 · Cooling · AI agents · Python · +2 stars measured 2026-10-27, 00:39–13:33 UTC, ≈ 5 by evening
   A RouterHub guide and prompt collection for GLM 5.3 abliterated/uncensored models, bundling 35 jailbreak prompt files plus API and coding-tool setup notes.
   Full card: https://gitnova.dev/en/r/routerhubSI/glm-5.3-abliterated.md
2. **Andreas698/glm-5.3-uncensored** — 5.7 · Early signal · AI agents · Python · +1 star measured 2026-10-27, 00:34–13:22 UTC, ≈ 24 by evening
   A collection of 35 jailbreak and system-prompt files for GLM 5.3 and other LLMs, plus a guide to RouterHub API access covering GPT, Claude, DeepSeek, Qwen and Grok.
   Full card: https://gitnova.dev/en/r/Andreas698/glm-5.3-uncensored.md
3. **7API/glm-5.3-abliterated** — 1.1 · Cooling · Language models · +3 stars measured 2026-10-27, 00:00–13:39 UTC, ≈ 5 by evening
   A guide and prompt collection for GLM 5.3 abliterated/uncensored models, with 35 jailbreak prompts and access through a single OpenAI- and Anthropic-compatible 7API key.
   Full card: https://gitnova.dev/en/r/7API/glm-5.3-abliterated.md
4. **Alejandros17487/ai-jailbreaks** — 1.9 · Cooling · Security · +4 stars measured 2026-10-27, 00:39–13:33 UTC, ≈ 9 by evening
   A collection of 35 paste-ready jailbreak prompts for 25+ models: system prompts, AGENTS.md files, Modelfiles and configs for AI red-teaming and security research.
   Full card: https://gitnova.dev/en/r/Alejandros17487/ai-jailbreaks.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-27 13:44 UTC, updated every 30 minutes.