Evaluating Bgs Mods

What it does

When your agent uses it

• Deciding whether a mod belongs in a modpack — judging mod quality
• Pack-value BEFORE download/install
• - should I add this mod
• Is this mod good

Example prompts

• “should I add this mod”
• “is this mod good”
• “评估这个mod”
• “/evaluating-bgs-mods”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

1. 1Read the author's 说明 fully before judging. If it is English, translate it; the curator's job is to understand it anyway.
2. 2Prefer the original mod page/source when possible because it preserves the author 说明. A rehost with the same files but missing explanation…
3. 3If there is no author 说明 at all, reject by default. You cannot evaluate consequences that the author did not describe.
4. 4Check the publication/update date of recommendation articles and read across different authors/time periods. Community advice ages.
5. 5Prefer pure technical discussion signals over commercial-pack promotion signals when using community articles or forum posts.
6. 6Declare the pack 风格 before evaluating fit. A pack without a named style has no axis for "belongs".
7. 7Judge the mod against that 风格, not against screenshot appeal, novelty, or download gravity.
8. 8Ask whether the mod reinforces systemic feedback: behavior traceability, state propagation, consistent consequences.
9. 9Treat most data overlap as normal until there is evidence it causes a real problem; do not confuse overlap with failure.
10. 10On overlap, prefer the mod imposing a systemic unified rule over an incidental vanilla-record tweak that looks like 作者个人想法.
11. 11Account for scale: too many mechanics-changing or story/content-heavy additions can drown the pack's own style even if each mod is…
12. 12Name the mod's role in the pack. If future-you cannot tell why it exists, the pack will forget its own architecture.

What it can do on your machine

Read from SKILL.md and the folder at commit 9e7b281. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are dot).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evaluating Bgs Mods loads about 2.8k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 1,213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~124

When it runs · the whole SKILL.md, loaded when a task matches

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its Apache-2.0 licence (© hashgraph-online). 1,213 words, ~2,770 tokens.

name

evaluating-bgs-mods

description

Use when deciding whether a mod belongs in a modpack — judging mod quality, fit, risk, and pack-value BEFORE download/install. Triggers - "should I add this mod", "is this mod good", "评估这个mod", "这个mod值得装吗", "is this mod worth it", "this mod looks too good to be true", "compare these mods", "does this mod fit my pack". NOT for how to install a mod (use interpreting-mod-author-instructions), load order (writing-bgs-load-order), or conflict resolution (xedit-conflict-audit).

+-----------------------------------------------------------------------------------------------+
| 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. |
+-----------------------------------------------------------------------------------------------+

digraph evaluating_bgs_mods {
  rankdir=TB;
  node [shape=box];

  start [shape=doublecircle, label="Mod candidate"];
  read_page [label="Read the mod page fully\n(author description, requirements, warnings, articles)"];
  classify [label="Classify mod type\n(system rule? content? mechanics? visuals? patch?)"];
  systemic [label="Systemic-fit check\nDoes it reinforce state feedback?\nQuery KB for game-specific facts"];
  quality [label="Quality signals\n说明 quality, source integrity, article date, technical discussion"];
  risk [label="Risk signals\nNo说明, scale, script/off-switch risk, object-density, incidental edits\nQuery KB"];
  packfit [label="Pack-fit check\nDeclared 风格? redundant?\nSystemic-rule vs incidental edit?"];
  value [shape=diamond, label="Risk worth pack value?"];
  include [shape=doublecircle, label="INCLUDE\nthen hand off to install-instruction skill"];
  conditional [shape=doublecircle, label="CONDITIONAL INCLUDE\nname conditions + hand off only after met"];
  reject [shape=doublecircle, label="REJECT\nrecord why, do not download/install"];

  start -> read_page -> classify -> systemic -> quality -> risk -> packfit -> value;
  value -> include [label="clear fit, risks understood"];
  value -> conditional [label="fit plausible, missing proof/conditions"];
  value -> reject [label="off-style, unreadable risk, or low systemic value"];
}

bgs_kb_query({
  query: "<mod type> risk signals",
  domains: ["install-planning", "engine"],
  games: ["<current game>"]
})

bgs_kb_query({
  query: "mod-evaluation community operational signals",
  domains: ["install-planning", "engine"],
  games: ["<current game>"]
})

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/BB-84C/bgs-modding-superpowers/skills/evaluating-bgs-mods of hashgraph-online/awesome-codex-plugins.

Open the folder on GitHubat commit 9e7b281