awesome-ChatGPT-repositories is a curated, searchable directory of open-source repositories related to ChatGPT, the OpenAI API, and Codex. It is for people looking for tools such as retrieval systems, agent libraries, chatbot interfaces, and command-line utilities, with catalogue entries that support searching the collection through coding-agent extensions.
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.
git clone --depth 1 https://github.com/taishi-i/awesome-ChatGPT-repositoriesWrote 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/commands/taishi-i/awesome-chatgpt-repositories/awesome-chatgpt)<a href="https://agentmods.dev/commands/taishi-i/awesome-chatgpt-repositories/awesome-chatgpt"><img src="https://agentmods.dev/badge/commands/taishi-i/awesome-chatgpt-repositories/awesome-chatgpt/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/commands/taishi-i/awesome-chatgpt-repositories/awesome-chatgpt"><img src="https://agentmods.dev/badge/commands/taishi-i/awesome-chatgpt-repositories/awesome-chatgpt.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 | $0.00000 | $0.02531 |
| Opus 5 | $0.00000 | $0.01265 |
| Sonnet 5 | $0.00000 | $0.00506 |
| Haiku 4.5 | $0.00000 | $0.00253 |
Grade A, and why
awesome-chatgpt 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
The user's query is: $ARGUMENTS
Instructions
Step 1 — Interpret the query
Supported modifiers:
category:<name>— filter to one categorylanguage:<lang>— filter by programming languagelist categories/categories— show category list instead- Plain text — keyword search
The data descriptions are in English. Convert non-English queries to English keywords before searching.
Keyword tips:
- Use stems, not full words. Substring match catches variants:
embed→ embedding/embeddings,retriev→ retrieval/retrieve,fine-tun→ fine-tune/fine-tuning,summari→ summarize/summarization,classif→ classification/classifier,orchestrat→ orchestration/orchestrate. - Add domain-specific names. For common LLM/AI domains, include well-known tool names present in the database:
| Domain (query hint) | Stem keywords | Tool/library names to add |
|---|---|---|
| RAG / 検索拡張生成 | retriev, rag, embed, vector |
langchain, llamaindex, haystack, faiss, chroma, pinecone |
| Agent / エージェント | agent, autonom, orchestrat |
autogpt, langchain, langgraph, crewai |
| Fine-tuning / ファインチューニング | fine-tun, lora, peft, finetun |
lora, peft, qlora |
| Code generation / コード生成 | code, coding, copilot, autocomplet |
copilot, codex, interpreter |
| Chatbot / チャットボット | chat, bot, dialog, convers |
discord, telegram, slack |
| Prompt engineering | prompt, few-shot, chain-of-thought, jailbreak |
promptflow, dspy |
| Evaluation / 評価 | evaluat, benchmark, metric |
evals, lm-eval, deepeval |
- Aim for 3–6 keywords. Too few miss items; too many inflate low-quality partial matches.
Step 2 — Search the data files with grep
Data files are in plugins/awesome-chatgpt-search/data/ (relative to repo root / PWD). Each file is a JSON array with one repo record per line, so grep can pull only the matching repos instead of loading whole files (much lower token cost).
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.
- 13d ago First seen · 187 lines · 0 tokens per session scan A 1caebe99811e
awesome-chatgpt is a command published in the GitHub repository taishi-i/awesome-ChatGPT-repositories (3,242 stars, last pushed 5d ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 2,531 tokens. 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 commands, from other repositories
AGENTS
Per-command agent-optimized usage and structure guide.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.