Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/avinashp/agentsatlas/refactoringnpx skills add AvinashP/AgentsAtlas --skill refactoringgit clone --depth 1 https://github.com/AvinashP/AgentsAtlasWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.01215 |
| Opus 5 | $0.00014 | $0.00607 |
| Sonnet 5 | $0.00006 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
refactoring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Skill
Restructure code safely while preserving behavior.
Workflow
1. Verify Test Coverage
Before refactoring, ensure tests exist:
# Run existing tests
npm test
pytest
go test ./...
If no tests cover the code:
- Write characterization tests first
- These capture current behavior (even if buggy)
- Then refactor with confidence
2. Understand Current Structure
Map the code:
- What are the dependencies?
- Who calls this code?
- What does it depend on?
- What's the data flow?
# Find usages
grep -r "functionName" --include="*.ts"
# Find dependencies
grep -r "import.*from.*module" --include="*.ts"
3. Plan the Refactoring
Identify the target state:
- What's the problem with current code?
- What's the desired structure?
- What's the smallest step toward that?
Choose your approach:
| Situation | Approach |
|---|---|
| Large function | Extract methods |
| Duplicated code | Extract shared function |
| Complex conditionals | Replace with polymorphism |
| Long parameter list | Introduce parameter object |
| Feature envy | Move method to data's class |
| Data clump | Extract class |
4. Execute in Small Steps
The safe refactoring cycle:
1. Make ONE small change
2. Run tests
3. Commit if green
4. Repeat
Never skip steps:
- Don't combine multiple refactorings
- Don't "fix bugs" while refactoring
- Don't add features while refactoring
5. Verify Behavior Preserved
# Run full test suite
npm test
# Check for regressions
npm run test:e2e
# Manual smoke test if needed
Quick Reference
Safe Refactorings (Automated)
Most IDEs can do these automatically:
| Refactoring | Shortcut (VS Code) |
|---|---|
| Rename | F2 |
| Extract function | Ctrl+Shift+R |
| Extract variable | Ctrl+Shift+R |
| Inline variable | Ctrl+Shift+R |
| Move to file | Drag in explorer |
Common Patterns
Extract Function
// Before
function processOrder(order) {
// validate
if (!order.items.length) throw new Error('Empty order');
if (!order.customer) throw new Error('No customer');
// calculate total
let total = 0;
for (const item of order.items) {
total += item.price * item.quantity;
}
// apply discount
if (order.coupon) {
total *= (1 - order.coupon.discount);
}
return { ...order, total };
}
// After
function processOrder(order) {
validateOrder(order);
const total = calculateTotal(order);
return { ...order, total };
}
function validateOrder(order) {
if (!order.items.length) throw new Error('Empty order');
if (!order.customer) throw new Error('No customer');
}
function calculateTotal(order) {
const subtotal = order.items.reduce(
(sum, item) => sum + item.price * item.quantity,
0
);
return order.coupon
? subtotal * (1 - order.coupon.discount)
: subtotal;
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 240 lines · 28 tokens per session scan A 7a6f29596d88
refactoring is a skill published in the GitHub repository AvinashP/AgentsAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,215 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
eval-hooks
Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
eval-skills
Audit all skills in the current project for frontmatter completeness, effort level appropriateness, allowed-tools scoping, and content quality. Produces a scored report with effort-level recommendations for each skill. Use when onboarding to a new project, reviewing skill quality before shipping, or adding effort…
autoresearch
Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves.