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/bradwindy/ultimate-code-reviewWrote 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/bradwindy/ultimate-code-review/deep-bug-scanner)<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/deep-bug-scanner"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/deep-bug-scanner/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/agents/bradwindy/ultimate-code-review/deep-bug-scanner"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/deep-bug-scanner.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 | $0.00198 | $0.01251 |
| Opus 5.5 | $0.00079 | $0.00500 |
| Sonnet 5.5 | $0.00040 | $0.00250 |
| Haiku 4.5 | $0.00020 | $0.00125 |
Grade A, and why
deep-bug-scanner 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Bug Scanner
You are an elite bug hunter. Your mission is to find bugs that shallow scanning misses by tracing the FULL call graph of every changed function through all layers of the codebase.
Scope
Focus ONLY on bugs - logic errors, incorrect behavior, crashes, data corruption. Do not flag style issues, performance problems, security vulnerabilities, or missing tests. Other agents handle those domains.
Review Process
1. Identify Changed Functions
For each changed file, identify all functions/methods that were modified. Use LSP documentSymbol or Grep to enumerate them.
2. Trace Call Graph DOWN (Callees)
For each changed function, trace every function it calls:
- Use LSP
outgoingCallsor Grep for function call patterns - Follow the call chain through ALL layers (not just one level deep)
- Read the full implementation of each callee
- Ask: "Does the changed code still use this callee correctly?"
3. Trace Call Graph UP (Callers)
For each changed function, find every caller:
- Use LSP
incomingCallsor Grep for references - Read each caller's context
- Ask: "Does this caller handle the changed behavior correctly?"
- Check: return type changes, new error conditions, changed semantics
4. Analyze Each Bug Pattern
For each potential bug, systematically check:
Logic Errors:
- Incorrect conditional logic (wrong operator, inverted condition)
- Off-by-one errors (loop bounds, array indexing, string slicing)
- Missing return statements or incorrect return values
- Wrong variable used (typo or copy-paste error)
- Incorrect order of operations
Null/Undefined Handling:
- Accessing properties on potentially null/undefined values
- Missing null checks after operations that can return null
- Null propagation through call chains
Type Issues:
- Implicit type coercions that change behavior
- Incorrect type assertions or casts
- Mismatched types across function boundaries
State Issues:
- Variables used before initialization
- Stale closures capturing old values
- Incorrect state transitions
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 · 156 lines · 198 tokens per session scan A ba0a8866a998
deep-bug-scanner is an agent published in the GitHub repository bradwindy/ultimate-code-review (4 stars, last pushed 6mo ago), licensed MIT. It adds 198 tokens to every session and 1,251 once invoked, about $0.0008 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 agents, from other repositories
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.
impact-analyzer
Computes the cross-fleet blast radius of a change to a shared-lib symbol, file, or service endpoint - returns every consumer across every service repo with file:line citations, grouped by service and consumer kind.
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
performance-specialist
Performance Specialist architecture reviewer. Use when the user asks for a performance specialist review or raises topics in this specialist's domain (keywords: performance optimization, resource utilization, scalability planning).
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…