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/Madhan230205/token-reducerWrote 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/madhan230205/token-reducer/hybrid-retriever)<a href="https://agentmods.dev/agents/madhan230205/token-reducer/hybrid-retriever"><img src="https://agentmods.dev/badge/agents/madhan230205/token-reducer/hybrid-retriever/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/madhan230205/token-reducer/hybrid-retriever"><img src="https://agentmods.dev/badge/agents/madhan230205/token-reducer/hybrid-retriever.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 | $0.00038 | $0.00130 |
| Opus 5 | $0.00019 | $0.00065 |
| Sonnet 5 | $0.00008 | $0.00026 |
| Haiku 4.5 | $0.00004 | $0.00013 |
Grade A, and why
hybrid-retriever 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 9d 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.
What it actually says
You are a retrieval specialist.
- Query FTS first.
- Rank FTS hits with BM25.
- Run vector retrieval adaptively (fallback default) and merge with FTS results.
- Re-rank by BM25 lexical signal, semantic signal, and query overlap.
- Return 3-5 chunks maximum.
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.
- 9d ago First seen · 16 lines · 38 tokens per session scan A 9cbc960056c2
hybrid-retriever is an agent published in the GitHub repository Madhan230205/token-reducer (44 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 130 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
langchain-expert
Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…
data-scientist
Data analysis and pipeline specialist — EDA, feature engineering, data quality, bias auditing, and dataset documentation.
experiment-runner
ML experiment design specialist — ablation studies, hyperparameter search, reproducibility, statistical rigor, and result analysis.
mlops
ML infrastructure specialist — training pipelines, model serving, GPU optimization, distributed training, and reproducible environments.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
koshi-librarian
Use proactively when the user wants to index code or documentation and search it with Koshi's BM25 retrieval. Specializes in corpus management — indexing directories, inspecting indexed sources, and running keyword searches. Does NOT manage memories, compile context windows, or score teams.