dutchy313

LLM Callsite Checker — Data & AI agent for Claude Code

Data & AI community

Confirms or rejects static-scan findings about LLM calls in ONE source file and returns a short verdict per finding.

How to install LLM Callsite Checker

Installs to ~/.claude/agents/dutchy313-ai-cost-optimizer-llm-callsite-checker.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dutchy313/ai-cost-optimizer/HEAD/.claude/agents/llm-callsite-checker.md -o ~/.claude/agents/dutchy313-ai-cost-optimizer-llm-callsite-checker.md

Restart Claude Code, or start a new session, for it to be picked up.

What LLM Callsite Checker does

name: llm-callsite-checker description: Confirms or rejects static-scan findings about LLM calls in ONE source file and returns a short verdict per finding. Use only when the ai-cost-optimizer agent hands over a file path and its findings. tools: Read, Grep model: haiku effort: low maxTurns: 6

You check heuristic findings about LLM API calls in a single file. You are a fast, narrow reviewer. Do not explore the repository, suggest refactors or edit anything.

Input: a file path and a lis

Alternatives in Data & AI

  • Info Disclosure — Information Disclosure specialist (H1 #18, CWE-200/209/215/538/668/798) 812 ★
  • Rlm Subcall — Acts as the RLM sub-LLM (llm_query) 382 ★
  • Patina Naturalness Reviewer — Triggers to re-scan a patina rewrite for residual AI tells and over-editing risk 352 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Design Copy Editor — Data & AI agent for Claude Code

Design Copy Editor

Stage 3c of the world-class-design process. Treats every AI-written line in a design as placeholder and rewrit

Data & AI community
Wikiskill Grader — Data & AI agent for Claude Code

Wikiskill Grader

Strict LLM-judge grader — given a task's success criteria and an inference agent's transcript/final answer, re

Data & AI community
Npl Perf Profiler — Data & AI agent for Claude Code

Npl Perf Profiler

Static C++ performance analysis specialist for high-performance database proxy systems, focusing on memory pat

Data & AI community
Conversation Assessor — Data & AI agent for Claude Code

Conversation Assessor

Reads one exported batch of conversations and writes one verdict file inside work/results/. Use it only for tr

Data & AI community
Forge Data Integrity — Data & AI agent for Claude Code

Forge Data Integrity

Forge's Data Integrity & Migration agent — validates schema migrations for destructive operations and checks m

Data & AI community
Guide Reviewer — Data & AI agent for Claude Code

Guide Reviewer

Vérifier accuracy factuelle, détecter marketing speak, checker anti-AI markers (em dashes, staccato), tone Bol

Data & AI community

Related Skills

Code Audit — Security skill for Claude Code

Code Audit

Adversarial code review tree. Wraps /cc-tree:tree with the code-audit preset preselected — finds security / pe

Security community
Review Fix Loop — Development skill for Claude Code

Review Fix Loop

Run a review, fix the findings, and review again until no blocker or major findings remain. Use when the user

Development community
Mem Gate — Data skill for Claude Code

Mem Gate

Hard write-rules quality gate — scan existing memory for junk entries that violate the data-quality canon, or

Data community