
- Installs
- 851
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/boshu2/agentops --skill complexity- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads complexity automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Complexity Skill
YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
Analyze code complexity to identify refactoring targets.
Execution Steps
Given /complexity [path]:
Step 1: Determine Target
If path provided: Use it directly.
If no path: Use current directory or recent changes:
git diff --name-only HEAD~5 2>/dev/null | grep -E '\.(py|go)$' | head -10
Step 2: Detect Language
# Check for Python files
ls *.py **/*.py 2>/dev/null | head -1 && echo "Python detected"
# Check for Go files
ls *.go **/*.go 2>/dev/null | head -1 && echo "Go detected"
Step 3: Run Complexity Analysis
For Python (using radon):
# Check if radon is installed
which radon || pip install radon
# Run cyclomatic complexity
radon cc <path> -a -s
# Run maintainability index
radon mi <path> -s
For Go (using gocyclo):
# Check if gocyclo is installed
which gocyclo || go install github.com/fzipp/gocyclo/cmd/gocyclo@latest
# Run complexity analysis
gocyclo -over 10 <path>
Step 4: Interpret Results
Cyclomatic Complexity Grades:
| Grade | CC Score | Meaning |
|---|---|---|
| A | 1-5 | Low risk, simple |
| B | 6-10 | Moderate, manageable |
| C | 11-20 | High risk, complex |
| D | 21-30 | Very high risk |
| F | 31+ | Untestable, refactor now |
Step 5: Identify Refactor Targets
List functions/methods that need attention:
- CC > 10: Should refactor
- CC > 20: Must refactor
- CC > 30: Critical, immediate action
Step 6: Write Complexity Report
Write to: .agents/complexity/YYYY-MM-DD-<target>.md
# Complexity Report: <Target>
**Date:** YYYY-MM-DD
**Language:** <Python/Go>
**Files Analyzed:** <count>
## Summary
- Average CC: <score>
- Highest CC: <score> in <function>
- Functions over threshold: <count>
## Refactor Targets
### Critical (CC > 20)
| Function | File | CC | Recommendation |
|----------|------|-----|----------------|
| <name> | <file:line> | <score> | <how to simplify> |
### High (CC 11-20)
| Function | File | CC | Recommendation |
|----------|------|-----|----------------|
| <name> | <file:line> | <score> | <how to simplify> |
## Refactoring Recommendations
1. **<Function>**: <specific suggestion>
- Extract: <what to extract>
- Simplify: <how to simplify>
## Next Steps
- [ ] Address critical complexity first
- [ ] Create issues for high complexity
- [ ] Consider refactoring sprint
Step 7: Report to User
Tell the user:
- Overall complexity summary
- Number of functions over threshold
- Top 3 refactoring targets
- Location of full report
- Run
/refactor <function>to address critical complexity targets
Key Rules
- Use the right tool - radon for Python, gocyclo for Go
- Focus on high CC - prioritize 10+
- Provide specific fixes - not just "refactor this"
- Write the report - always produce artifact
Quick Reference
Simplifying High Complexity:
- Extract helper functions
- Replace conditionals with polymorphism
- Use early returns
- Break up long functions
- Simplify nested loops
Examples
Analyzing Python Project
User says: /complexity src/
What happens:
- Agent detects Python files in
src/directory - Agent checks for radon installation, installs if missing
- Agent runs
radon cc src/ -a -sfor cyclomatic complexity - Agent runs
radon mi src/ -sfor maintainability index - Agent identifies 3 functions with CC > 20, 7 functions with CC 11-20
- Agent writes detailed report to
.agents/complexity/2026-02-13-src.md - Agent recommends extracting nested conditionals in
process_request()function
Result: Complexity report identifies process_request() (CC: 28) as critical refactor target with specific extraction recommendations.
Finding Refactor Targets in Go Module
User says: /complexity
What happens:
- Agent checks recent changes with
git diff --name-only HEAD~5 - Agent detects Go files, verifies gocyclo installation
- Agent runs
gocyclo -over 10 ./...on project - Agent finds
HandleWebhook()function with complexity 34 - Agent writes report with recommendation to extract validation logic
- Agent reports top 3 targets: HandleWebhook (34), ProcessBatch (22), ValidateInput (15)
Result: Critical function identified for immediate refactoring with actionable extraction plan.
See Also
- refactor — Safe, verified refactoring for complexity targets
Troubleshooting
| Problem | Cause | Solution |
|---|---|---|
| Tool not installed (radon/gocyclo) | Missing dependency | Agent auto-installs: pip install radon for Python or go install github.com/fzipp/gocyclo/cmd/gocyclo@latest for Go. Verify install path in $PATH. |
| No complexity issues found | Threshold too high or genuinely simple code | Lower threshold: try gocyclo -over 5 or check if path includes actual implementation files vs tests. |
| Report shows functions without recommendations | Generic analysis without codebase context | Read the high-CC functions to understand structure, then provide specific refactoring suggestions based on actual code patterns. |
| Mixed language project | Multiple languages in target path | Run analysis separately per language: /complexity src/python/ then /complexity src/go/, combine reports manually. |
Reference Documents
- references/complexity.feature — Executable spec: rank functions by cyclomatic complexity, scope to recent changes by default, focused hotspot list (soc-qk4b)
FAQ
What does the complexity skill do?
Find focused refactor hotspots.
How do I install complexity?
Run npx skills add https://github.com/boshu2/agentops --skill complexity in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/complexity/ (personal) or .claude/skills/complexity/ (project).
Which AI agents can use complexity?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is complexity safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains complexity?
It is published by boshu2 in boshu2/agentops. It has 851 recorded installs.
More from boshu2/agentops
council
boshu2/agentops
Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.
doc
boshu2/agentops
Write source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.
research
boshu2/agentops
Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.
plan
boshu2/agentops
Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.
swarm
boshu2/agentops
Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".
rpi
boshu2/agentops
Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.