fix-bugs

fix-bugs is a command for Claude Code from dachivadachkoria/claude-code-starter-kit. It costs 17 tokens per session (1,215 once invoked), scanned A, original, MIT.

A bug-fixing command that scans code for common mistakes and anti-patterns, including errors in asynchronous code and program logic.

In plain words
What is it for?
Use it on changed files or selected code to identify issues and apply common fixes.
Why use it?
It helps find small but serious defects—such as missed values, unclosed files, missing await statements, and incorrect conditions—that are easy to overlook during development.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it on changed files or selected code to identify issues and apply common fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dachivadachkoria/claude-code-starter-kit/fix-bugs
Install

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.

Clone the repo
git clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fix-bugs

README.md
[![agentmods](https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs/github.svg)](https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs)
Your own site
<a href="https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs"><img src="https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fix-bugs

Your own site · 80×15
<a href="https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs"><img src="https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.01215
Opus 5.5 $0.00007 $0.00486
Sonnet 5.5 $0.00003 $0.00243
Haiku 4.5 $0.00002 $0.00121

Measured 1mo ago against content hash 3800f92d14d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix-bugs 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 1mo 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.

.claude/commands/fix-bugs.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Detection & Auto-Fix

Scan and fix issues in: $ARGUMENTS (default: changed files)

Detection Categories

1. Common Bugs

Null/Undefined Handling

# Bug: AttributeError if user is None
user.name  

# Fix: Safe navigation
user.name if user else None
# Or: getattr(user, 'name', None)

Off-by-One Errors

# Bug: Misses last element
for i in range(len(items) - 1):

# Fix: Include last element
for i in range(len(items)):

Resource Leaks

# Bug: File handle not closed on error
f = open('file.txt')
data = f.read()
f.close()

# Fix: Context manager
with open('file.txt') as f:
    data = f.read()

2. Async Issues

Missing await

# Bug: Returns coroutine, not result
async def get_user():
    return fetch_user(id)  # Missing await!

# Fix
async def get_user():
    return await fetch_user(id)

Blocking in async context

# Bug: Blocks event loop
async def process():
    time.sleep(1)  # Blocking!

# Fix: Use async sleep
async def process():
    await asyncio.sleep(1)

3. Logic Errors

Boolean Expression Bugs

# Bug: Always True
if x == 1 or 2:

# Fix
if x == 1 or x == 2:
# Or: if x in (1, 2):

Mutable Default Arguments

# Bug: Shared list across calls
def add_item(item, items=[]):
    items.append(item)
    return items

# Fix: Use None default
def add_item(item, items=None):
    if items is None:
        items = []
    items.append(item)
    return items

4. Type Issues

Type Coercion Problems

// Bug: String concatenation instead of addition
const total = "5" + 3;  // "53"

// Fix: Explicit conversion
const total = Number("5") + 3;  // 8

5. Security Issues

Injection Vulnerabilities

# Bug: SQL Injection
query = f"SELECT * FROM users WHERE id = {user_id}"

# Fix: Parameterized query
query = "SELECT * FROM users WHERE id = %s"
cursor.execute(query, (user_id,))

Execution Flow

Step 1: Identify Targets

Read the full file on GitHub · 227 lines

Changes

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.

  1. 1mo ago First seen · 227 lines · 17 tokens per session scan A 3800f92d14d7

Subscribe to this mod's changes

fix-bugs is a command published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 1,215 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other commands, from other repositories

subagent-diagnose

Multi-agent failure-investigation orchestrator. Parallel to /subagent-implementation — same scratchpad + investigator + builder/surgeon + reviewer + FOLLOWUPS pattern — but starts from a failure, not a spec. Two modes share one loop: ci (failed CI run is the brief seed) and bug (freeform symptom paragraph is the brief…

damusix/atomic-claude · 0 tokens

quick-fix

Implement→review subagent loop with no planning phase, for a fix whose cause is known and whose shape is obvious, however many files it touches. No spec, no worktree, no docs or signals at the end; one audit. Routes to /subagent-diagnose on an unknown cause and to /atomic-plan on an open approach or contract choice.

damusix/atomic-claude · 73 tokens

sdlc-cycle

An automated software development life-cycle (SDLC) workflow covering an issue or plan, coding, tests, verification, and a pull or merge request.

LeeYudok/agents-scaffold · 41 tokens

quick-fix

Minimal-token bug fix -- direct fix with no exploration.

Sagargupta16/claude-cost-optimizer · 10 tokens

knowledge-graph

A visual map of how project guidance files are connected, including rules, memories, agents, skills, commands, and workflows. It generates a local HTML dashboard and can check whether their links still work.

LeeYudok/agents-scaffold · 0 tokens

fix-issue

A workflow for handling a numbered software issue from investigation through delivery. It reads the issue, changes the code, adds a regression test, verifies the build, and prepares a pull or merge request.

LeeYudok/agents-scaffold · 3 tokens