skill-refresh
- Repo stars 435
- Author updated Live
- Author repo nvim
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @benbrastmckie · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: skill-refresh
description: Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Dir…
category: engineering
runtime: no special runtime
---
# skill-refresh output preview
## PART A: Task fit
- Use case: Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Direct execution skill for managing OpenCode resources. Performs two operations: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Execution / Step 1: Parse Arguments / Step 2: Run Process Cleanup” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Direct execution skill for managing OpenCode resources. Performs two operations: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Execution / Step 1: Parse Arguments / Step 2: Run Process Cleanup” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/refresh`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Execution / Step 1: Parse Arguments / Step 2: Run Process Cleanup”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skill-refresh
description: Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Dir…
category: engineering
source: benbrastmckie/nvim
---
# skill-refresh
## When to use
- Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Direct execution skill fo…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Execution / Step 1: Parse Arguments / Step 2: Run Process Cleanup” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skill-refresh" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Execution / Step 1: Parse Arguments / Step 2: Run Process Cleanup
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Refresh Skill (Direct Execution)
Direct execution skill for managing OpenCode resources. Performs two operations:
- Process cleanup: Identify and terminate orphaned OpenCode processes
- Directory cleanup: Clean up accumulated files in ~/.opencode/
This skill executes inline without spawning a subagent.
Execution
Step 1: Parse Arguments
Extract flags from command input:
--dry-run: Preview mode--force: Skip confirmation, use 8-hour default
# Parse from command input
dry_run=false
force=false
if [[ "$*" == *"--dry-run"* ]]; then
dry_run=true
fi
if [[ "$*" == *"--force"* ]]; then
force=true
fi
Step 2: Run Process Cleanup
Execute process cleanup script:
.opencode/scripts/claude-refresh.sh $( [ "$force" = true ] && echo "--force" )
Store process cleanup output for display.
Step 3: Clean Orphaned Postflight Markers
Clean any orphaned postflight coordination files from the specs directory. These files should normally be cleaned up by skills after postflight completes, but may be left behind if a process is interrupted.
echo ""
echo "=== Cleaning Orphaned Postflight Markers ==="
echo ""
# Find orphaned postflight markers (older than 1 hour)
orphaned_pending=$(find specs -maxdepth 3 -name ".postflight-pending" -mmin +60 -type f 2>/dev/null)
orphaned_guard=$(find specs -maxdepth 3 -name ".postflight-loop-guard" -mmin +60 -type f 2>/dev/null)
# Also check for legacy global markers
legacy_pending=""
legacy_guard=""
if [ -f "specs/.postflight-pending" ]; then
legacy_pending="specs/.postflight-pending"
fi
if [ -f "specs/.postflight-loop-guard" ]; then
legacy_guard="specs/.postflight-loop-guard"
fi
if [ -n "$orphaned_pending" ] || [ -n "$orphaned_guard" ] || [ -n "$legacy_pending" ] || [ -n "$legacy_guard" ]; then
if [ "$dry_run" = true ]; then
echo "Would delete the following orphaned markers:"
[ -n "$orphaned_pending" ] && echo "$orphaned_pending"
[ -n "$orphaned_guard" ] && echo "$orphaned_guard"
[ -n "$legacy_pending" ] && echo "$legacy_pending"
[ -n "$legacy_guard" ] && echo "$legacy_guard"
else
# Delete orphaned task-scoped markers
find specs -maxdepth 3 -name ".postflight-pending" -mmin +60 -delete 2>/dev/null
find specs -maxdepth 3 -name ".postflight-loop-guard" -mmin +60 -delete 2>/dev/null
# Delete legacy global markers
rm -f specs/.postflight-pending 2>/dev/null
rm -f specs/.postflight-loop-guard 2>/dev/null
echo "Cleaned orphaned postflight markers."
fi
else
echo "No orphaned postflight markers found."
fi
Step 4: Clean Stale Backup Files
Scan for and remove any .backup files left over from the deprecated backup mechanism in .opencode/:
echo ""
echo "=== Cleaning Stale Backup Files ==="
echo ""
# Find .backup files in .opencode/ directory
backup_files=$(find .opencode/ -name "*.backup" -type f 2>/dev/null)
if [ -n "$backup_files" ]; then
backup_count=$(echo "$backup_files" | wc -l)
if [ "$dry_run" = true ]; then
echo "Would delete $backup_count .backup file(s):"
echo "$backup_files"
else
echo "$backup_files" | xargs rm -f
echo "Deleted $backup_count stale .backup file(s)."
fi
else
echo "No stale .backup files found."
fi
Step 5: Run Directory Survey
Show current directory status without cleaning yet:
.opencode/scripts/claude-cleanup.sh
This displays:
- Current ~/.opencode/ directory size
- Breakdown by directory
- Space that can be reclaimed
Step 6: Execute Based on Mode
Dry-Run Mode
If --dry-run is set:
echo ""
echo "=== DRY RUN MODE ==="
echo "Showing 8-hour cleanup preview..."
echo ""
.opencode/scripts/claude-cleanup.sh --dry-run --age 8
Exit after showing preview.
Force Mode
If --force is set:
echo ""
echo "=== EXECUTING CLEANUP (8-hour default) ==="
echo ""
.opencode/scripts/claude-cleanup.sh --force --age 8
Show results and exit.
Interactive Mode (Default)
If neither flag is set:
Check if cleanup candidates exist (claude-cleanup.sh exits with code 1 if candidates found)
If no candidates, display message and exit:
No cleanup candidates found within default thresholds.
All files are either protected or recently modified.
- If candidates exist, prompt user for age selection:
{
"question": "Select cleanup age threshold:",
"header": "Age Threshold",
"multiSelect": false,
"options": [
{
"label": "8 hours (default)",
"description": "Remove files older than 8 hours - aggressive cleanup"
},
{
"label": "2 days",
"description": "Remove files older than 2 days - conservative cleanup"
},
{
"label": "Clean slate",
"description": "Remove everything except safety margin (1 hour)"
}
]
}
Map user selection to age parameter:
- "8 hours (default)" →
--age 8 - "2 days" →
--age 48 - "Clean slate" →
--age 0
- "8 hours (default)" →
Execute cleanup with selected age:
case "$selection" in
"8 hours (default)")
.opencode/scripts/claude-cleanup.sh --force --age 8
;;
"2 days")
.opencode/scripts/claude-cleanup.sh --force --age 48
;;
"Clean slate")
.opencode/scripts/claude-cleanup.sh --force --age 0
;;
esac
- Display cleanup results
Example Execution Flows
Interactive Flow
# User runs: /refresh
# Output:
OpenCode Refresh
===================
No orphaned processes found.
All 3 Claude processes are active sessions.
---
OpenCode Directory Cleanup
=============================
Target: ~/.opencode/
Current total size: 7.3 GB
Scanning directories...
Directory Total Cleanable Files
---------- ------- ---------- -----
projects/ 7.0 GB 6.5 GB 980
debug/ 151.0 MB 140.0 MB 650
...
TOTAL 7.3 GB 6.7 GB 5577
Space that can be reclaimed: 6.7 GB
# Prompt appears:
[Age Threshold]
Select cleanup age threshold:
1. 8 hours (default) - Remove files older than 8 hours
2. 2 days - Remove files older than 2 days
3. Clean slate - Remove everything except safety margin
# User selects option 1
# Cleanup executes:
Cleanup Complete
================
Deleted: 5577 files
Failed: 0 files
Space reclaimed: 6.7 GB
New total size: 600.0 MB
Dry-Run Flow
# User runs: /refresh --dry-run
# Shows survey, then:
=== DRY RUN MODE ===
Showing 8-hour cleanup preview...
Would delete: 5577 files
Would reclaim: 6.7 GB
Dry Run Summary
===============
No changes made.
Force Flow
# User runs: /refresh --force
# Shows survey, then immediately:
=== EXECUTING CLEANUP (8-hour default) ===
Cleanup Complete
================
Deleted: 5577 files
Space reclaimed: 6.7 GB
Safety Measures
Protected Files (Never Deleted)
sessions-index.json(in each project directory)settings.json.credentials.jsonhistory.jsonl
Safety Margin
Files modified within the last hour are never deleted, regardless of age threshold.
Process Safety
- Only targets orphaned processes (TTY = "?")
- Never kills active sessions
- Excludes current process tree
Error Handling
Scripts Not Found
If scripts don't exist:
Error: Cleanup scripts not found at .opencode/scripts/
Please ensure claude-refresh.sh and claude-cleanup.sh are installed.
Permission Denied
If kill/delete fails due to permissions:
Warning: Some operations failed due to insufficient permissions.
Failed files: 5
Successfully deleted: 5572 files
No ~/.opencode/ Directory
If directory doesn't exist:
Error: ~/.opencode/ directory not found.
Nothing to clean up.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review