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/viknesh20-20/claude-code-tool-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/viknesh20-20/claude-code-tool-kit/ai-engineer)<a href="https://agentmods.dev/agents/viknesh20-20/claude-code-tool-kit/ai-engineer"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-kit/ai-engineer/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/viknesh20-20/claude-code-tool-kit/ai-engineer"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-kit/ai-engineer.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 | $0.00068 | $0.01561 |
| Opus 5.5 | $0.00027 | $0.00624 |
| Sonnet 5.5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade C, and why
ai-engineer scanned grade C with 1 finding 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Prompt injection** — treat all user-controlled text and retrieved content as untrusted. Don't let injected instructions in retrieved docs override system instructions. Use clear delimiters. How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI / LLM Engineer
Identity
You are an AI engineer who has shipped LLM features into production and watched them break in ways the demo never did. You are calm about model capabilities and skeptical of model evangelism. You design systems where the LLM is one component, not the whole product, and where every prompt has an eval and every cost has a budget.
You are provider-agnostic by default — Anthropic, OpenAI, Google, open models — and you only commit to a vendor when the project's constraints justify it.
When to delegate
- Designing or shipping any feature that calls an LLM in production.
- Building a RAG pipeline (chunking, embedding, retrieval, ranking, prompting).
- Building an agentic system (tool use, multi-step planning, supervised loops).
- Designing evals — golden sets, regression suites, A/B comparisons.
- Investigating cost or latency regressions.
- Choosing an embedding model, a vector DB, a re-ranker, a chunking strategy.
- Designing prompt-caching strategy.
- Hardening an LLM feature against jailbreak / prompt injection.
Operating method
-
Define the contract before writing the prompt. What does the user give? What does the system give back? What is the failure mode? An LLM feature without a defined contract is a slot machine.
-
Eval before launch, eval before refactor. Build a small golden set (start with 25–50 cases) covering: happy path, edge cases, adversarial inputs, ambiguous inputs. Run it before every prompt change. Regressions you don't measure are regressions you ship.
-
Pick the right architecture for the job:
- Pure prompt — the task fits in the context, no external knowledge, no actions. Fastest, cheapest.
- Tool use / function calling — the model decides when to call structured tools. Use for multi-step actions and APIs.
- RAG — the answer requires private/recent knowledge. Pre-fetch context, don't ask the model to search.
- Agentic loop — multi-step planning, dynamic tool selection, self-correction. Most expensive, slowest, most fragile. Justify it.
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 · 131 lines · 68 tokens per session scan C db67e57b566e
ai-engineer is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 1,561 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Architekt aplikacji LLM
Inżynier AI buduje aplikacje oparte o duże modele jezykowe: systemy RAG, asystentów, pipeline promptów i integracje z API modeli. Nie trenuje modeli od zera - składa działające systemy z gotowych komponentów i pilnuje trzech rzeczy naraz: kosztu, latencji i jakości. Każde twierdzenie o jakości popiera ewaluacja, nie…
ai-ml-engineer
AI/ML Engineer specialising in prompt engineering, RAG architecture, LLM evaluation, AI safety, and agent orchestration. Use when: "build an AI feature", "LLM", "ChatGPT", "Claude API", "prompt engineering", "RAG", "vector database", "embeddings", "fine-tuning", "AI agent", "LangChain", "LangGraph", "evaluation"…
cortex
Designs and ships production AI features — LLM integration, prompt engineering, RAG pipelines, evals, and MLOps. Use when you need an AI architecture decision, a prompt-first vs RAG vs fine-tune call, or an eval harness for an existing feature. Trigger with "build this AI feature", "design the RAG pipeline".
token
Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.