Awesome Codex Plugins is a curated catalogue and marketplace of installable plugins, skills, and related resources for OpenAI Codex and ChatGPT. It helps people find, create, validate, and submit extensions for Codex workflows across its app, command-line interface, and IDE extensions. The catalogue add-ons are the plugins, skills, agents, and hooks listed or supported by this project.
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 hashgraph-online/awesome-codex-plugins --skill curating-bgs-modpackgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/curating-bgs-modpack)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/curating-bgs-modpack"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/curating-bgs-modpack/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/hashgraph-online/awesome-codex-plugins/curating-bgs-modpack"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/curating-bgs-modpack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.02888 |
| Opus 5.5 | $0.00055 | $0.01155 |
| Sonnet 5.5 | $0.00027 | $0.00578 |
| Haiku 4.5 | $0.00014 | $0.00289 |
Grade A, and why
curating-bgs-modpack 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 2mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curating BGS Modpack (judgment skill)
A BGS modpack is not a shopping cart of impressive files. It is a declared world-style, built in recoverable increments, with enough naming, attribution, and rollback discipline that future-you can still explain what every layer is doing. Stability is the floor. 风格 is the soul. The curator is co-authoring a systemic world, not proving they can install more mods than a Vault-Tec procurement clerk can misfile requisitions.
The Iron Law
+------------------------------------------------------------------------------------------------+
| Declare the pack's 风格 first, then add mods in named, reversible batches; if you cannot say |
| what role a batch plays or how to roll it back, you are stockpiling files, not curating a pack. |
+------------------------------------------------------------------------------------------------+
Route gate (one primary skill per intent)
Use this skill when the question is how to build or reshape the whole pack: declared style, batch sizing, rollback boundaries, separators, naming convention, attribution, and devlog discipline.
Do not use this skill as the primary skill for adjacent intents:
| User intent | Primary skill |
|---|---|
| "Should this mod be included?" / judge quality, risk, and pack fit | evaluating-bgs-mods |
| "How do I install this mod correctly?" / read author instructions / choose files or FOMOD options | interpreting-mod-author-instructions |
| Record a pack decision, batch boundary, or lesson learned | writing-modpack-devlog |
Enable/disable/sort plugins.txt or loadorder.txt |
writing-bgs-load-order |
| Inspect actual conflicts, winning overrides, or whether reorder-vs-patch is safe | xedit-conflict-audit |
Terminal handoff: after this skill defines the style and next batch boundary, hand each candidate mod to evaluating-bgs-mods. After a batch decision is made, hand the decision to writing-modpack-devlog. Inclusion says "belongs in the next plan"; it does not mean "install loose files however you feel like it."
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.
- 2mo ago First seen · 193 lines · 137 tokens per session scan A 725cc6315a2e
curating-bgs-modpack is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (1,517 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 2,888 once invoked, about $0.0005 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 2026-08-30.
curating-bgs-modpack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| curating-bgs-modpackhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 137 | Claude Code, Codex |
| awesome-chatgpttaishi-i/awesome-ChatGPT-repositories | Skill | 3.4k | yesterday | CC0-1.0 | A | 79 | Claude Code |
| awesome-chatgpt-searchtaishi-i/awesome-ChatGPT-repositories | Skill | 3.4k | yesterday | CC0-1.0 | B | 63 | Claude Code, Codex |
| procedural-gengamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 88 | Claude Code |
| bprrwilsonfreitas/awesome-quant | Skill | 30k | yesterday | none | A | 61 | Claude Code, Codex |
| drawio-reconstructionHKUSTDial/Supervisor-Skills | Skill | 12k | yesterday | none | A | 102 | Codex |
| benchmark-paper-templateHKUSTDial/Supervisor-Skills | Skill | 12k | yesterday | none | A | 96 | Claude Code, Codex |