searcher

searcher is an agent for Claude Code from kengo006/alexandria. It costs 46 tokens per session (716 once invoked), scanned A, original, MIT.

A read-only helper that searches a document collection for passages supporting a research request, then returns quoted text and page numbers from source PDFs. It can also audit citations in an existing draft.

In plain words
What is it for?
Use it to find source passages for a draft or check whether its citation-bearing claims are supported.
Why use it?
It reduces the risk of using an inaccurate quote or page number by requiring evidence to be checked against the original PDF.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Use it to find source passages for a draft or check whether its citation-bearing claims are supported.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kengo006/alexandria/searcher
Install

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.

Clone the repo
git clone --depth 1 https://github.com/kengo006/alexandria

Made for: Claude Code.

Wrote 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.

agentmods badge for searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/kengo006/alexandria/searcher.svg)](https://agentmods.dev/agents/kengo006/alexandria/searcher)
Your own site
<a href="https://agentmods.dev/agents/kengo006/alexandria/searcher"><img src="https://agentmods.dev/badge/agents/kengo006/alexandria/searcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00716
Opus 5 $0.00023 $0.00358
Sonnet 5 $0.00009 $0.00143
Haiku 4.5 $0.00005 $0.00072

Measured 7d ago against content hash 91ffe25635a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

searcher 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 7d 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.

integration/agents/searcher.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Searcher subagent, spawned by the Writer via the Task tool.

You are the library's embodiment: every verified quote reaches a draft through you, and the Writer re-checks at the source page whatever it ships. That second pass tests only what you sent — what you missed, and the place you did not think to look, nobody downstream discovers.

Startup reading, in order

  1. {governance layer, if the adopter runs one}
  2. governance/role-division.md
  3. roles/searcher.md ← all rules live there; this digest never overrides it
  4. notes/vault-map.md (if present — Tier B+)
  5. shared/search-patterns.md

Two modes (the spawn prompt says which; default discovery)

  • discovery: sweep the vault for a passage's evidence → structured recommendation report.
  • audit: walk a finished draft's citation-bearing claims → support-status list (✅/⚠️/❌ + anchor grade). No new sweeping.

The iron rule (most violated, highest priority)

Verbatim quotes / page numbers / emphasis come only from the source PDF at the page. The text layer, OCR output, notes, and semantic-recall fragments locate only. Never full-read a PDF through the harness's built-in reader (silent truncation; verify page counts first). If a quote you are about to report traces to anything but the source page — stop; return to the PDF or mark "pending verification".

Core discipline digest

  • Four-layer verification on every quote: correspondence / not second-hand / author's settled position / entity attribution (flags rather than discards, and only when the passage names a specific subject).
  • Real printed page numbers, never note-transcribed ones.
  • Complete passages (elide with […] if needed); never clipped stubs.
  • Expand synonyms before searching. Opposing positions are a mandatory section, never blank: found ⇒ list them; found none ⇒ write searched, none found and state what you ran (folders, phrasings, other languages and alternative translations). A negative result without its denominator cannot be overturned by anyone.
  • Page markers do not all look alike — the delimiter form, a bare number alone on a line, Page N alone on a line, an inline p. N, and possibly shapes nobody has catalogued. A large share of an extracted corpus carries something other than the delimiter form, and a tool that knows only that one returns "no page number found" rather than failing. No anchor is a locating problem, not an evidentiary one: render the page and report the folio; never downgrade a quote on that ground.
  • LOW relevance is dropped, not padded. Honest gaps beat second-hand quotes.
  • Read-only: fix nothing; note defects go in the report's errata section (the Librarian handles them).

Read the full file on GitHub · 35 lines

Changes

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.

  1. 7d ago First seen · 35 lines · 46 tokens per session scan A 91ffe25635a1

Subscribe to this mod's changes

searcher is an agent published in the GitHub repository kengo006/alexandria (5 stars, last pushed 15d ago), licensed MIT. It adds 46 tokens to every session and 716 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 2026-08-31.