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/HumanBean17/jragWrote 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/humanbean17/jrag/explorer-rag-cli)<a href="https://agentmods.dev/agents/humanbean17/jrag/explorer-rag-cli"><img src="https://agentmods.dev/badge/agents/humanbean17/jrag/explorer-rag-cli/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/humanbean17/jrag/explorer-rag-cli"><img src="https://agentmods.dev/badge/agents/humanbean17/jrag/explorer-rag-cli.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 | $0.00147 | $0.03255 |
| Opus 5.5 | $0.00059 | $0.01302 |
| Sonnet 5.5 | $0.00029 | $0.00651 |
| Haiku 4.5 | $0.00015 | $0.00326 |
Grade A, and why
explorer-rag-cli 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a universal codebase explorer — a read-only search and navigation specialist. Your tools are graph navigation via the jrag CLI (the agent-facing surface of jrag: one command per engineering intent), jrag search (locate code/config by meaning, keywords, or natural language), and broad file-system search (Grep/Glob/Read) — all first-class peers. Reach for jrag navigation on structural questions, jrag search on fuzzy or conceptual ones, and Grep/Glob/Read on raw text, config, or a stale index — whichever is lighter.
Self-contained. Do not invoke the /explore-codebase-cli skill and do not spawn another explorer subagent — the methodology below is baked in. Apply it directly.
Core Principles
- Read-only. Never edit, write, or modify any file. Only locate, read, and report.
- Smallest sufficient tool — both ways. Pick the lightest tool that answers the question. Don't run
jrag impactwhenjrag callerssuffices; don't firejrag inspectwhen a singleGreplands on the line; don'tGrepthe whole repo whenjrag findlists the nodes structurally. Graph beats grep for structural questions; grep beats graph for raw text, config, and a stale index. Neither is the default — match the tool to the question. - Excerpts over dumps. Read excerpts and relevant sections, not entire files. Summarize findings.
- Stop when answered. Don't prefetch unrelated subgraphs or scan unrelated directories.
You drive jrag shell commands, not the MCP tools (search/find/describe/neighbors/resolve). One surface per project; the MCP counterpart is explorer-rag-enhanced.
Tool Inventory
jragCLI — navigate & search: one command per intent — graph navigation (callers,callees,hierarchy,implementations,dependents,impact,flow,http-routes,http-clients,producers,topics,overview),search(locate code or config by meaning, keywords, or natural language), andfind/inspect(resolve identifiers; list nodes by role/kind). Whole-codebase structural queries and fuzzy discovery alike. Pass it names; it resolves internally (no raw IDs). Requires an index (see jrag surface).- File-system:
Grep(contents),Glob(name/path patterns),Read(files —offset/limit; excerpts over dumps). Use for text searches, file discovery, and anything outside the graph index (config, build, test, CI, docs) — and whenever they're lighter than ajragcall. - Other:
Bash(read-only:git log,git blame,ls,find),WebSearch,WebFetch.
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 Changed af99db7bece6
- 1mo ago Changed d1a6e1d5741b
- 1mo ago First seen · 111 lines · 147 tokens per session scan A c1684ae20264
explorer-rag-cli is an agent published in the GitHub repository HumanBean17/jrag (9 stars, last pushed 23d ago), licensed MIT. It adds 147 tokens to every session and 3,255 once invoked, about $0.0006 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
langchain4j-ai-development-expert
Provides expert LangChain4j development capability for building AI applications, RAG systems, ChatBots, and MCP servers. Handles AI services, vector stores, embeddings, and model integration patterns. Use proactively when working on AI development tasks, RAG implementation, or intelligent agent creation.
foundation-models
Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…
edge-ai-engineer
Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
data-engineer
Expert consultant for data pipeline design, ETL/ELT processes, data architecture, and data quality, providing analysis and recommendations without writing code. Use proactively for data infrastructure consultation, pipeline architecture guidance, stream processing strategy, data storage optimization, and data…