MDX-Tom/gpt-instruct
A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。
About the project
A prompt and test pack for Codex (GPT) that alters model behavior on complex tasks: improves first-pass execution, process continuity and artifact verification. Includes a deploy/rollback script for Codex config.
Useful for
- Deploy a prompt into CODEX_HOME via codex-instruct.py with rollback support
- Run A/B/C regression tests to evaluate a candidate prompt
- Compare prompt versions by cases, turns and artifact gate metrics
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 30 stars today.
- Interest is fading: the two-day pace is 48% of the previous week and a half.
- Top new repositories in the last 4 months: #45.
- About 9 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 8,192
- Stars in a day
- 30
- Forks
- 1,016
- Issues and pull requests
- 73
- Watchers
- 32
- Language
- Python
- License
- MIT
- Latest release
- gpt-6-astra-v1 · September 6, 2026
- Created
- July 11, 2026
- Last push
- September 7, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026Top new repositories in the last 4 months: #45
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.