Writing Modpack Devlog logo

Writing Modpack Devlog

OrganizationPopular
hashgraph-online
writing-modpack-devlog

Use when starting or appending to a modpack project dev-log. Creates <project>/docs/dev-log.md if absent; appends a dated entry on subsequent calls. Triggers - 'log this', 'add to dev log', 'record what I did', 'note this change', 'devlog'.

Overview

Publisherhashgraph-online
Repositoryawesome-codex-plugins
Skill namewriting-modpack-devlog
Stars
1.3K
Forks
360
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by hashgraph-online on GitHub. Read the source before you install it.

Installation

Install the Writing Modpack Devlog AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/BB-84C/bgs-modding-superpowers/skills/writing-modpack-devlog
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git /tmp/awesome-codex-plugins
mkdir -p .claude/skills
cp -r /tmp/awesome-codex-plugins/plugins/BB-84C/bgs-modding-superpowers/skills/writing-modpack-devlog .claude/skills/writing-modpack-devlog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Modpack Devlog in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Writing Modpack Devlog on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Writing Modpack Devlog is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

The modpack dev-log is the durable record of what the curator did to the modpack, in chronological order, with enough context for a future maintainer to understand why a change happened. This skill replaces the deleted templates/modpack/dev-log.md template by creating <project>/docs/dev-log.md at runtime, then appending entries as the modpack evolves.

When to Use

Use this skill when...Result
The user says "log this", "add to dev log", "record what I did", or "note this change"Append a dated entry to the project dev-log.
A mod was added, removed, replaced, upgraded, downgraded, patched, or moved in load orderRecord what changed and why.
A conflict-audit session finishedSummarize the finding and link evidence from xedit-conflict-audit or xedit-automation output.
A CTD, freeze, missing asset, bad facegen, navmesh issue, or broken quest was investigatedPreserve the investigation result, even if the fix is not final.
A modpack release was cutAdd the curator-facing note and cross-link to writing-modpack-changelog.
The user made a manual decision that future agents must not re-litigateRecord the decision, context, and evidence.

When NOT to Use

Do not use this skill when...Use instead
The user is preparing public release notes for playerswriting-modpack-changelog
The user asks for a one-off explanation without wanting a project recordAnswer directly.
The project root is unknown and the user refuses to identify itStop after explaining what is missing.
The entry would expose private notes, credentials, or personal informationAsk for a sanitized version first.
The request is to inspect or edit plugin recordsxedit-automation or xedit-conflict-audit first, then log the result.

Rules

  1. Detect the modpack project root before writing.
    • If the user provides <modpack_project_root>, use it.
    • If the current working directory looks like a modpack directory because it already has Data/, profiles/, or docs/, default to pwd and tell the user what default you used.
    • Otherwise ask once: "Which modpack project root should I use? I can default to the current directory if this is the project root."
  2. Locate <project>/docs/dev-log.md.
    • If <project>/docs/ does not exist, create it.
    • If dev-log.md is missing, create it before appending.
  3. On first creation, use this header shape:
    • # <Project Name> Dev Log
    • Started: <local ISO-8601 timestamp with offset>
    • A short note that entries are newest-first.
    • ## Entries
  4. Use local time with UTC offset for every entry timestamp, and keep that choice consistent throughout the file.
    • Example: 2026-06-01T14:30:00-04:00.
    • Do not mix local dates, UTC dates, and vague dates such as "today".
  5. Each entry must include these parts:
    • ISO-8601 timestamp with offset.
    • Short title.
    • Body paragraph or paragraphs explaining what changed and why.
    • Optional Mods touched subsection when specific mods, plugins, patches, or tools were involved.
    • Optional Refs subsection linking evidence, logs, issue threads, release pages, or xEdit captures.
  6. Append entries newest-first under the ## Entries section.
    • Insert the new entry immediately below ## Entries.
    • Do not append new entries at the bottom unless the file already uses oldest-first and the user explicitly wants to keep it that way.
  7. Do not duplicate the most recent entry.
    • Read the newest entry timestamp and title.
    • If the new title and body would be identical or effectively identical within 10 minutes of the newest entry, surface: "This looks like a duplicate of <existing title> from <timestamp>. Append anyway? (y/N)"
    • Default to no if the user does not confirm.
  8. Preserve evidence when the user references it.
    • If the user points at a captured xEdit conflict, crash log, plugin diff, screenshot, text log, or other local evidence file, copy it into <project>/docs/dev-log-artifacts/<entry-slug>/.
    • Link the copied artifact from the entry body or Refs subsection.
    • Prefer copying over linking to a fragile temporary path.
  9. Make the entry useful to a future curator.
    • Include the decision, cause, tradeoff, or unresolved question.
    • Avoid entries that only say "fixed stuff" or "updated mods".
  10. Keep private working noise out of the dev-log.
    • Do not paste entire terminal transcripts unless they are the evidence.
    • Summarize the result, then link artifacts.
  11. If the user gave rough notes, preserve meaning rather than polishing away operational details.
    • Keep mod names, plugin names, load-order context, symptoms, and reproduction facts.
    • Clean up grammar only enough to make the entry readable.
  12. After writing, report the file path, entry title, timestamp, and any artifacts copied.

Quick Reference

FieldCanonical shapeExample
File<project>/docs/dev-log.mddocs/dev-log.md
Entry heading### <timestamp> - <short title>### 2026-06-01T14:30:00-04:00 - Rebuilt settlement patch after lighting update
BodyOne or more paragraphs explaining what changed and whyUpdated the settlement compatibility patch after the lighting mod changed precombines in the affected cells.
Mods touchedOptional bullet list- Example Lighting Overhaul
RefsOptional bullet list of copied artifacts or external references- dev-log-artifacts/rebuilt-settlement-patch/xedit-conflict-summary.md

Canonical entry shape:

markdown
### 2026-06-01T14:30:00-04:00 - Rebuilt settlement patch after lighting update

Updated the settlement compatibility patch after the lighting mod changed records in the affected cells. The new patch keeps the visual change while preserving the workshop keyword edits from the settlement overhaul.

#### Mods touched

- Example Lighting Overhaul
- Example Settlement Overhaul
- Example Modpack Patch

#### Refs

- dev-log-artifacts/rebuilt-settlement-patch/xedit-conflict-summary.md

Examples

Bad

markdown
Fixed the lighting thing.

This entry has no date, no mod names, no context, no evidence, and no explanation of what was fixed.

Good

markdown
### 2026-06-01T14:30:00-04:00 - Resolved lighting and workshop keyword conflict

Kept the lighting overhaul's cell image-space change, but restored the settlement overhaul's workshop keyword edits in the patch. This should preserve the intended visual pass without breaking workshop placement in the affected settlement.

#### Mods touched

- Example Lighting Overhaul
- Example Settlement Overhaul
- Example Modpack Patch

#### Refs

- dev-log-artifacts/lighting-workshop-keyword-conflict/xedit-conflict-summary.md

This entry tells a future curator what changed, why it changed, which mods were involved, and where the evidence lives.

Common Mistakes

  • Writing a loose note without a timestamp.
  • Logging only the action and omitting the reason.
  • Using the dev-log as public release notes instead of curator history.
  • Duplicating the same entry because the user repeated "log this" after a tool run.
  • Linking to temporary evidence paths that will disappear.
  • Copying huge raw logs into the main entry instead of summarizing and linking artifacts.
  • Recording "updated mods" without naming the mods.
  • Turning rough curator notes into generic prose that loses load-order context.
  • Asking multiple root-location questions instead of one question with a default.
  • Creating the file somewhere outside the actual modpack project root.

Rationalizations

ExcuseReality
"This is just a tiny note; it does not need structure."Tiny notes become the only record future agents can trust. Date, title, context, and refs are the minimum useful shape.
"The release changelog will cover it."The changelog is for players. The dev-log is for curators and future agents. They answer different questions.
"The evidence is in my terminal scrollback."Scrollback is not durable. Copy evidence into docs/dev-log-artifacts/<entry-slug>/ and link it.
"I can append at the bottom; it is easier."Newest-first keeps the current state visible. Insert below ## Entries unless the user explicitly chose oldest-first.
"The user knows what they meant by 'lighting thing'."Future maintainers will not. Name the symptom, mod, plugin, cell, record, or decision.
"I should ask several questions to make sure the entry is perfect."Ask once for the project root if needed. Otherwise write the best entry from available context and flag uncertainties inline.
"The artifact path is already linked in the conversation."Conversation links are not project records. Copy or preserve the artifact in the project docs tree.
"I should make this sound polished."Accuracy beats polish. Keep the operational facts and make the wording readable.

See also

  • writing-modpack-changelog - use for player-facing release notes and version sections.
  • setting-up-bgs-modding-environment - use when the modpack project structure itself is being created or located.

Frequently asked questions

What does the Writing Modpack Devlog AI skill do?

Use when starting or appending to a modpack project dev-log. Creates <project>/docs/dev-log.md if absent; appends a dated entry on subsequent calls. Triggers - 'log this', 'add to dev log', 'record what I did', 'note this change', 'devlog'.

Why use Writing Modpack Devlog on TypingMind?

Because you install it once and use it with any model. Writing Modpack Devlog is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Writing Modpack Devlog in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/BB-84C/bgs-modding-superpowers/skills/writing-modpack-devlog. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Writing Modpack Devlog?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Writing Modpack Devlog?

As many as you like. As long as a model supports skills, you can use Writing Modpack Devlog with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Writing Modpack Devlog AI skill free?

Yes. It is published on GitHub by hashgraph-online under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇