these prompts for Claude Sonnet 5.5 and Opus 5.5 are ridiculous. 7 sections you paste above any task. they set the standard instead of describing the work. the best one: if Sonnet can't crack a hard problem after a second attempt, it tells you to hand it to Opus, with the goal,
@godofprompt
-
OpenAI model writes 722 math research papers
By
–
OpenAI just published 722 maths papers written by a model they haven't released. 372 result families across the whole field. they posed the model around 4,000 open research problems and each result took about 3 hours of thinking compute. some of what's in there: a zero-free
-
Google engineer open-sources 25 agent skills for engineering workflow
By
–
a Google engineer packed his entire engineering workflow into agent skills and put the whole thing on Github. it's Addy Osmani, who runs Chrome developer experience. 25 skills covering the full lifecycle, from interviewing you about what you actually want through to shipping and
-
Hindsight tool gives coding agents repo memory from git history
By
–
found a tool called Hindsight for that annoying moment when your coding agent has no idea what you worked on yesterday.
— God of Prompt (@godofprompt) 6 octobre 2026
it reads your git history and past sessions, keeps a memory bank for each repo, and passes that context to the agent when you start again. saves you from… pic.twitter.com/khxJWA5xm6found a tool called Hindsight for that annoying moment when your coding agent has no idea what you worked on yesterday. it reads your git history and past sessions, keeps a memory bank for each repo, and passes that context to the agent when you start again. saves you from
-
Coding agent audits harness and cuts wasted tokens
By
–
paste this into your coding agent and it audits your harness, finds everything being resent on every turn for nothing, and cuts it. it starts by instrumenting what isn't being logged, then renders your real requests and counts tokens section by section. you get a ranked list of
-
Codex agent packages repeated workflows into reusable skills
By
–
paste this into Codex and it goes through your last 30 days of sessions, memories and history, finds the workflows you've done more than once, and packages them. it checks what you already have first, so it extends an existing skill instead of making a duplicate. it gives you
-
Trick to stop AI agents forgetting tasks via AGENTS.md
By
–
here's a trick that stops your agent forgetting every task you give it, so you never have to re-explaining for the same thing twice paste this into your AGENTS. md and it stops doing one-off work. anything you ask for that could happen again gets built into a skill file and put
-
Split agent system prompts into modular skill folders
By
–
stop stuffing your entire workflow into one giant system prompt. your agent reads all of it on every task, including the 90% that has nothing to do with what you just asked. split it into skills instead. one folder per job, one markdown file in each. only the name and a
-
Dots agent prompt turns chatbot into a daily operator
By
–
one prompt into your Dots agent and you're 10x more productive by tomorrow. 12 sections that turn it from a chatbot that happens to stay open into an actual operator. it holds a live picture of everything competing for your attention, plans your day around your real calendar
-
GitHub repo collects leaked AI chatbot system prompts
By
–
someone's been extracting the hidden instructions every AI chatbot gets before your first message, and putting them on Github.
— God of Prompt (@godofprompt) 1 octobre 2026
68,700 stars. Fable 5.1, GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5, Grok 4.7, GPT-6 Luna. captured word for word, updated constantly.
read a few… pic.twitter.com/uF1PZjq6HOsomeone's been extracting the hidden instructions every AI chatbot gets before your first message, and putting them on Github. 68,700 stars. Fable 5.1, GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5, Grok 4.7, GPT-6 Luna. captured word for word, updated constantly. read a few