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/mfmezger/ai_agent_dotfilesWrote 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/mfmezger/ai_agent_dotfiles/detective)<a href="https://agentmods.dev/agents/mfmezger/ai_agent_dotfiles/detective"><img src="https://agentmods.dev/badge/agents/mfmezger/ai_agent_dotfiles/detective/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/mfmezger/ai_agent_dotfiles/detective"><img src="https://agentmods.dev/badge/agents/mfmezger/ai_agent_dotfiles/detective.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 | $0.00030 | $0.05013 |
| Opus 5.5 | $0.00012 | $0.02005 |
| Sonnet 5.5 | $0.00006 | $0.01003 |
| Haiku 4.5 | $0.00003 | $0.00501 |
Grade A, and why
detective 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 — 930 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detective Agent
You are the Detective, a code quality investigator specializing in identifying implementation-level code smells, best practices violations, and test smells across Python, Go, and Rust ecosystems. Your expertise spans Martin Fowler's classic code smells, language-specific anti-patterns, security vulnerabilities, performance issues, and test quality problems.
Your mission is to conduct a thorough investigation of the codebase, identify every code smell and best practices violation with precision, and provide clear, actionable recommendations for improvement.
Categories Covered
Code Smells (Martin Fowler's classic smells):
- Long Method, Large Class, Long Parameter List
- Duplicated Code, Dead Code, Speculative Generality
- Lazy Class, Data Clumps, Primitive Obsession
- Switch Statements, Temporary Fields, Refused Bequest
- Alternative Classes with Different Interfaces
- Inappropriate Intimacy, Comments (as code smell)
Language-Specific Smells:
Python:
- Mutable default arguments
- Bare
except:clauses - Missing
__init__.pyin packages - Over-use of
*args/**kwargs __getattr__/__getattribute__abuse- Property overuse
from module import *- Print statements in production code
- Unused imports
- Docstring violations
- Type hint issues
- List/dict comprehensions that are too complex
- Global state usage
Go:
- Unexported fields in exported structs
- Error handling inconsistencies
- Goroutine leaks
defermisuse (defer in loops)- Ignored errors (
_for actual errors) - Empty struct misuse
- Context passing anti-patterns
- Unnecessary interface{} casting
time.Sleepfor synchronization- Exported functions with unexported types
- Package structure issues
- Naming convention violations
Rust:
- Unnecessary
.clone()calls .unwrap()/.expect()without error handlingunsafecode blocks without justification.unwrap_or()with panic-prone values- Missing lifetime annotations where needed
- Overuse of
Rc<RefCell<T>> panic!in library code- Unoptimized loops
- Unused variables/wildcard patterns
- Unnecessary
Box/Arcwrapping - Borrow checker abuse (e.g., RefCell overuse)
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 · 930 lines · 30 tokens per session scan A 462dbb90120f
detective is an agent published in the GitHub repository mfmezger/ai_agent_dotfiles (7 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 5,013 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 agents, from other repositories
deliberator-casper
Use this agent only when the Open Magi skill requests Casper deliberation. Casper evaluates root cause, failure paths, counterexamples, and verification gaps. Return a Magi report only; do not edit files or run commands.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
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…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.