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 agentmods add skills/hashgraph-online/awesome-codex-plugins/interpreting-mod-author-instructionsnpx skills add hashgraph-online/awesome-codex-plugins --skill interpreting-mod-author-instructionsgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWhat 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 | $0.00133 | $0.03931 |
| Opus 5 | $0.00067 | $0.01965 |
| Sonnet 5 | $0.00027 | $0.00786 |
| Haiku 4.5 | $0.00013 | $0.00393 |
Grade A, and why
interpreting-mod-author-instructions 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 yesterday.
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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interpreting Mod Author Instructions (judgment skill)
This skill answers one question only: How do I correctly download/install per the mod author's instructions? It starts after evaluating-bgs-mods has said INCLUDE or CONDITIONAL INCLUDE. The job is not to decide whether the mod is good; the job is to read the author's说明 until the install path, file choice, prerequisite order, option logic, and consequences are actually understood.
The Iron Law
+-----------------------------------------------------------------------------------------------+
| No author说明, no install plan: understand the author's requirements, variants, and consequences |
| before touching downloads, FOMOD options, files, profiles, or load-order state. |
+-----------------------------------------------------------------------------------------------+
Route gate (one primary skill per intent)
Use this skill when the user is asking how to install a mod that is already worth considering: which file to download, which variant to choose, how to read a FOMOD, what prerequisites must be present first, how to name/track the installed components, or what the author means by a warning.
Do not use this skill as the primary skill for adjacent intents:
| User intent | Primary skill |
|---|---|
| "Should I add this mod?" / quality, risk, fit, pack-value before install | evaluating-bgs-mods |
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 |
| Extract, inspect, or repack BA2/BSA archives | using-bgs-archive |
| Compile/decompile Papyrus PSC/PEX | using-bgs-papyrus |
| Translate plugin text or emit SST/XML dictionaries | using-bgs-translator |
Upstream gate: evaluating-bgs-mods. Inclusion says "worth considering"; it does not grant permission to install by habit.
Terminal handoff target: NONE. This skill ends with an install interpretation: selected file(s), selected option(s), prerequisite order, naming/tracking notes, and open gaps. If follow-on work requires archive/Papyrus/translator/tool operations, route to the existing tool skill for that operation.
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.
- yesterday First seen · 264 lines · 133 tokens per session scan A 00676415c18c
interpreting-mod-author-instructions is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (859 stars, last pushed 3d ago), licensed Apache-2.0. It adds 133 tokens to every session and 3,931 once invoked, about $0.0007 per session on Opus 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.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
preview-verdicts
Generate the interactive keep/drop verdict preview (HTML page with per-row feedback controls) whenever a prune sweep, batch entry edit, or restructure needs maintainer review before touching README.md — and process the feedback JSON the maintainer pastes back.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
check-mcp-json
Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.
awesome-web-security
Looks up curated web security learning resources (XSS, SQLi, CSRF, SSRF, OAuth/JWT, deserialization, SAML, recon, evasion, defensive tooling, CTF). Filters by topic, difficulty, language, and resource type. Returns top references with archive fallbacks. Defensive and educational use only.