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.
git clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kitWrote 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.
[](https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/fix-bugs)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 1mo ago First seen · 227 lines · 17 tokens per session scan A 3800f92d14d7
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.
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…
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.
sdlc-cycle
An automated software development life-cycle (SDLC) workflow covering an issue or plan, coding, tests, verification, and a pull or merge request.
quick-fix
Minimal-token bug fix -- direct fix with no exploration.
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.
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.