XERJ is a local search tool that automatically indexes folders so coding agents can retrieve relevant code, documents, logs, and PDFs without reading files one at a time. It is for developers and agents using code search, retrieval-augmented generation, security audits, or agent memory.
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.
npx skills add xerj-org/xerj --skill xerj-knowledgegit clone --depth 1 https://github.com/xerj-org/xerjWrote 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/skills/xerj-org/xerj/xerj-knowledge)<a href="https://agentmods.dev/skills/xerj-org/xerj/xerj-knowledge"><img src="https://agentmods.dev/badge/skills/xerj-org/xerj/xerj-knowledge/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/skills/xerj-org/xerj/xerj-knowledge"><img src="https://agentmods.dev/badge/skills/xerj-org/xerj/xerj-knowledge.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 | $0.00067 | $0.00497 |
| Opus 5.5 | $0.00027 | $0.00199 |
| Sonnet 5.5 | $0.00013 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
xerj-knowledge 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 5d 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
Search local documents with XERJ
XERJ indexes a folder on this machine and returns ranked passages with their source. Nothing is uploaded: the index and the files stay local.
When to use it
- "Find the contract that mentions the renewal date", "what did we decide about the budget in the March notes", "which spreadsheet has the Q3 numbers".
- Any question whose answer is in the user's own documents rather than on the web or in a code base.
How
- If the folder is not indexed yet, index it once (it is incremental on
re-runs, so running it again only picks up changed files):
xerj autoindex "<folder>" --prefix <name>Pick a short<name>per folder (for examplenotes,mail,finance) and reuse it. - Search with the MCP tool
xerj_search(a plain-string query is fine), or on the command line:xerj search --prefix <name> "<plain words>". The ranking matches words, not meaning, so use the words the document would use: names, titles, figures, phrases. - Open the passage's source before relying on it when the answer matters.
Citing
- Every claim in the answer names its source as it was printed: the file path, plus the page (PDF), slide (PPTX), sheet (XLSX) or message (mail) when the hit carries one.
- If nothing relevant comes back, say so and say what was searched (folder and prefix). Do not fill the gap from memory.
Limits
- XERJ needs the
xerjbinary on PATH and a running local node for these tools. If the tool is missing or the node is down, tell the user how to start it (see the plugin README) instead of guessing an answer. - Scanned PDFs without a text layer have no text to search.
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.
- 5d ago First seen · 45 lines · 67 tokens per session scan A 24f36a6fc46e
xerj-knowledge is a skill published in the GitHub repository xerj-org/xerj (19,064 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 497 once invoked, about $0.0003 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 2026-11-01.
xerj-knowledge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xerj-knowledgexerj-org/xerj | Skill | 19k | today | Apache-2.0 | A | 67 | Claude Code |
| parse-documentsuperlinked/sie | Skill | 3.5k | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| superlinked-docssuperlinked/sie | Skill | 3.5k | yesterday | Apache-2.0 | A | 125 | Claude Code, Codex |
| pkf-writingPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 78 | Claude Code, Codex |
| liteparsePrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 173 | Claude Code, Codex |
| ingestPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 132 | Claude Code, Codex |
| ov-add-papervolcengine/OpenViking | Skill | 42k | yesterday | AGPL-3.0 | A | 55 | Claude Code |