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 evaluating-bgs-modsgit 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/evaluating-bgs-mods)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/evaluating-bgs-mods"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/evaluating-bgs-mods/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/evaluating-bgs-mods"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/evaluating-bgs-mods.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 | $0.00128 | $0.02441 |
| Opus 5.5 | $0.00051 | $0.00976 |
| Sonnet 5.5 | $0.00026 | $0.00488 |
| Haiku 4.5 | $0.00013 | $0.00244 |
Grade A, and why
evaluating-bgs-mods 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluating BGS Mods (judgment skill)
BGS games are systems simulators, not stage plays: the pack is trying to build a world where behavior leaves traces, state feeds back, and stories happen because systems collide. A mod is not admitted because it looks impressive in isolation; it is admitted when it reinforces the pack's declared 风格 and the game's systemic feedback loop. Stability is the floor. 风格 is the soul.
The Iron Law
+-----------------------------------------------------------------------------------------------+
| A mod earns a place in the pack only by fitting the pack's declared 风格 AND reinforcing the |
| game's systemic feedback -- popularity, screenshots, and download counts are inputs, never fit. |
+-----------------------------------------------------------------------------------------------+
Route gate (one primary skill per intent)
Use this skill when the decision is whether the mod belongs in the pack at all: quality, fit, risk, redundancy, and pack-value before download/install.
Do not use this skill as the primary skill for adjacent intents:
| User intent | Primary skill |
|---|---|
| "How do I install this?" / read the author's instructions / choose installer options | interpreting-mod-author-instructions |
Edit, enable, disable, sort, or reason about plugins.txt / load order |
writing-bgs-load-order |
| Inspect actual records, winners, overrides, or conflict severity | xedit-conflict-audit |
Terminal handoff: after an INCLUDE or CONDITIONAL INCLUDE verdict, stop judging and hand the mod page to interpreting-mod-author-instructions. Inclusion says "worth considering"; it does not mean "install however you feel like it."
When to use / When NOT
Use when:
- The user asks "should I add this mod", "is this mod worth it", "这个mod值得装吗", or "does this fit my pack".
- A mod looks too good to be true and needs a judgment pass before download.
- Comparing multiple mods that claim to solve the same pack problem.
- Deciding whether a mod's edits are systemic rules or incidental 作者个人想法 fighting the pack.
- The pack already has a declared 风格 and the question is fit against that axis.
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 · 173 lines · 128 tokens per session scan A 930c59b7469a
evaluating-bgs-mods is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (1,537 stars, last pushed today), licensed Apache-2.0. It adds 128 tokens to every session and 2,441 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.
evaluating-bgs-mods compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evaluating-bgs-modshashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 128 | 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 | 7.8k | 11d ago | Apache-2.0 | A | 88 | Claude Code |
| bprrwilsonfreitas/awesome-quant | Skill | 31k | today | none | A | 61 | Claude Code, Codex |
| drawio-reconstructionHKUSTDial/Supervisor-Skills | Skill | 12k | 3d ago | none | A | 102 | Codex |
| benchmark-paper-templateHKUSTDial/Supervisor-Skills | Skill | 12k | 3d ago | none | A | 96 | Claude Code, Codex |