added opencode config
This commit is contained in:
@@ -365,7 +365,6 @@ exec --no-startup-id mullvad-vpn
|
|||||||
exec --no-startup-id redshift ~/.config/redshift/redshift.conf
|
exec --no-startup-id redshift ~/.config/redshift/redshift.conf
|
||||||
exec --no-startup-id blueman-applet
|
exec --no-startup-id blueman-applet
|
||||||
exec --no-startup-id picom -b
|
exec --no-startup-id picom -b
|
||||||
exec --no-startup-id flameshot
|
|
||||||
|
|
||||||
# locking specific startup applications
|
# locking specific startup applications
|
||||||
#exec --no-startup-id xss-lock --transfer-sleep-lock -- i3lock --nofork
|
#exec --no-startup-id xss-lock --transfer-sleep-lock -- i3lock --nofork
|
||||||
|
|||||||
@@ -0,0 +1,18 @@
|
|||||||
|
# Agent instructions
|
||||||
|
|
||||||
|
## Always do
|
||||||
|
|
||||||
|
- Before editing, briefly explain the intended change.
|
||||||
|
- Prefer small, focused diffs.
|
||||||
|
- Reuse existing patterns, think reusable and modular.
|
||||||
|
- Try to use functional approaches, if practical.
|
||||||
|
- Run tests or type checks after code changes when practical.
|
||||||
|
- Do not introduce new dependencies without asking.
|
||||||
|
- Update docs when behavior changes.
|
||||||
|
|
||||||
|
## Documentation Guidelines
|
||||||
|
|
||||||
|
- Use the with-context MCP server for all project documentation additionally
|
||||||
|
- Create changelogs in CHANGELOG.md using append mode
|
||||||
|
- Store API docs in docs/api/ folder
|
||||||
|
- Always set project context before writing notes
|
||||||
@@ -0,0 +1,7 @@
|
|||||||
|
---
|
||||||
|
description: Analyze token usage across the current session with detailed breakdowns by category
|
||||||
|
---
|
||||||
|
|
||||||
|
Call the tokenscope tool directly without delegating to other agents.
|
||||||
|
Leave sessionID unset unless the user explicitly asked to analyze a different session.
|
||||||
|
Then cat the token-usage-output.txt. DONT DO ANYTHING ELSE WITH THE OUTPUT.
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"$schema": "https://raw.githubusercontent.com/Opencode-DCP/opencode-dynamic-context-pruning/master/dcp.schema.json"
|
||||||
|
}
|
||||||
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"$schema": "https://opencode.ai/config.json",
|
||||||
|
"plugin": [
|
||||||
|
"superpowers@git+https://github.com/obra/superpowers.git",
|
||||||
|
"opencode-snip@latest",
|
||||||
|
"@tarquinen/opencode-dcp@latest",
|
||||||
|
"@ramtinj95/opencode-tokenscope",
|
||||||
|
"@slkiser/opencode-quota",
|
||||||
|
"envsitter-guard@latest",
|
||||||
|
"opencode-mystatus"
|
||||||
|
],
|
||||||
|
"command": {
|
||||||
|
"mystatus": {
|
||||||
|
"description": "Query quota usage for all AI accounts",
|
||||||
|
"template": "Use the mystatus tool to query quota usage. Return the result as-is without modification."
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"mcp": {
|
||||||
|
"with-context": {
|
||||||
|
"type": "local",
|
||||||
|
"command": ["npx", "-y", "with-context-mcp"],
|
||||||
|
"environment": {
|
||||||
|
"OBSIDIAN_API_KEY": "{env:OBSIDIAN_API_KEY}",
|
||||||
|
"OBSIDIAN_API_URL": "{env:OBSIDIAN_API_URL}",
|
||||||
|
"OBSIDIAN_VAULT": "{env:OBSIDIAN_VAULT}",
|
||||||
|
"PROJECT_BASE_PATH": "{env:PROJECT_BASE_PATH}"
|
||||||
|
},
|
||||||
|
"enabled": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
---
|
||||||
|
name: auto-commit
|
||||||
|
description: Use when you are making multiple edits or completing significant work in a git repository to automatically create commits
|
||||||
|
---
|
||||||
|
|
||||||
|
# Auto-Commit
|
||||||
|
|
||||||
|
## Overview
|
||||||
|
|
||||||
|
Create a git commit for each logical chunk of work completed. This keeps the commit history meaningful and gives you a safety net to undo if something goes wrong later.
|
||||||
|
|
||||||
|
## When to Use
|
||||||
|
|
||||||
|
- After completing a significant change (new feature, bug fix, refactor)
|
||||||
|
- After each logical step in a multi-step implementation
|
||||||
|
- Before switching context or getting interrupted
|
||||||
|
- When the diff is coherent and focused on one thing
|
||||||
|
|
||||||
|
## Do NOT commit for
|
||||||
|
|
||||||
|
- Trivial single-line fixes
|
||||||
|
- Changes that are still in progress / incomplete
|
||||||
|
- When the user explicitly says not to
|
||||||
|
|
||||||
|
## How
|
||||||
|
|
||||||
|
1. When you finish a piece of work, run `git status` and `git diff` to understand the changes
|
||||||
|
2. Use `git add` to stage relevant files
|
||||||
|
3. Create a commit with a message that explains WHAT changed and WHY (inspired by conventional commits but adapted to the project's style)
|
||||||
|
4. Run `git status` after to verify
|
||||||
|
|
||||||
|
## Commit Message Style
|
||||||
|
|
||||||
|
- First line: concise summary (max 72 chars)
|
||||||
|
- Format: `type: short description`
|
||||||
|
- Types: `feat`, `fix`, `refactor`, `test`, `docs`, `chore`, `style`
|
||||||
|
- Body (optional): additional context if needed
|
||||||
|
- Reference issues or related commits if applicable
|
||||||
Reference in New Issue
Block a user