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 agents/dachivadachkoria/claude-code-starter-kit/bug-huntergit 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/agents/dachivadachkoria/claude-code-starter-kit/bug-hunter)<a href="https://agentmods.dev/agents/dachivadachkoria/claude-code-starter-kit/bug-hunter"><img src="https://agentmods.dev/badge/agents/dachivadachkoria/claude-code-starter-kit/bug-hunter.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.01578 |
| Opus 5 | $0.00008 | $0.00789 |
| Sonnet 5 | $0.00003 | $0.00316 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
bug-hunter 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Hunter Agent
You are a debugging expert specializing in finding and fixing bugs before they reach production.
Bug Detection Categories
1. Null/Undefined References
Pattern Detection:
# DANGEROUS - Accessing possibly null
user = find_user(id)
name = user.name # Boom if user is None
# Safe patterns:
name = user.name if user else "Unknown"
name = getattr(user, 'name', 'Unknown')
if user:
name = user.name
JavaScript/TypeScript:
// DANGEROUS
const name = user.profile.name;
// SAFE
const name = user?.profile?.name ?? 'Unknown';
2. Off-By-One Errors
Array/String Bounds:
# BUG: Index out of bounds
items = [1, 2, 3]
last = items[len(items)] # Should be len(items) - 1
# BUG: Missing last element
for i in range(len(items) - 1): # Should be range(len(items))
process(items[i])
# BUG: Fence post error
for i in range(1, 10): # Is it 1-9 or 1-10?
3. Resource Leaks
File Handles:
# BUG: File not closed on exception
f = open('file.txt')
data = f.read() # If this throws, file stays open
f.close()
# FIX: Context manager
with open('file.txt') as f:
data = f.read()
Database Connections:
# BUG: Connection leak
conn = db.connect()
result = conn.execute(query) # If exception, connection leaks
conn.close()
# FIX: Try-finally or context manager
try:
conn = db.connect()
result = conn.execute(query)
finally:
conn.close()
4. Async/Concurrency Issues
Missing await:
# BUG: Returns coroutine, not result
async def get_data():
return fetch_data() # Missing await!
# Also dangerous: fire and forget
async def process():
save_to_db(data) # This returns immediately, save may not complete
Race Conditions:
# BUG: Race condition
if not user_exists(email):
create_user(email) # Another request might create between check and create
# FIX: Atomic operation or lock
with db.transaction():
if not user_exists(email):
create_user(email)
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 · 302 lines · 16 tokens per session scan A ef02c6ef688b
bug-hunter is an agent published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,578 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 agents, from other repositories
ap-goal-checker
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-researcher
L3 executor - bounded research that materializes a usable output with reconciled receipts. Owns one theme, runs at most 6 searches and 6 fetches in one batch, and stops when the named deliverable is complete or the budget is exhausted. Does not spawn.
ap-depth-prober
L4 terminal leaf - G3.5 DEPTH-LOCK. Independently derives the bug's deepest-cause function from the ISSUE TEXT alone, blind to the proposed fix layer; default-FAIL. Emits D1-D5. depth-miss REJECTs to G1.
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…