ReddRadar
Agent skill
minion-patch
Use when a mechanical code change needs review before applying. Delegates grunt work to local LLMs — saves cloud tokens. Generates patch for review. Use for changes that might need adjustment. Files must be <500 lines.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/minion-patch
SKILL.md
Minion Patch
Generate a patch for manual review.
When to Invoke
- Changes need careful review before applying
- User wants to see diff before commit
- Complex changes that might need adjustment
Command
source .venv/bin/activate && python scripts/minions.py --json patch "<task>" --target <file> --read <file>
Examples
# Generate patch
python scripts/minions.py --json patch "Add TODO comment at top" --target src/foo.py --read src/foo.py
# Multiple targets
python scripts/minions.py --json patch "Add header" --target src/a.py --target src/b.py --read src/a.py --read src/b.py
Output
{
"task": "Add TODO comment",
"patch_path": "sessions/20260112-123456.patch",
"summary": "Added comment to foo.py"
}
Applying Patches
# Review
cat sessions/*.patch
# Dry-run
patch -p1 --dry-run < sessions/*.patch
# Apply
patch -p1 < sessions/*.patch
Limits
- Files <500 lines (32K context)
- Mechanical changes only
- Always pass --read with target file
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?