searcher

searcher is a skill for Claude Code, Codex from kengo006/alexandria. It costs 68 tokens per session (372 once invoked), scanned A, original, MIT.

A read-only research role that finds sources in a document collection and returns exact, page-linked quotations. It can also check whether citations in a finished draft are supported by their sources.

In plain words
What is it for?
Use it to locate evidence, verify quotations and page numbers, check attribution, and audit citations in research writing.
Why use it?
It reduces the risk of using clipped, second-hand, wrongly attributed, or poorly located quotations. The description does not identify the document collection itself.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to locate evidence, verify quotations and page numbers, check attribution, and audit citations in research writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/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.

Any agent
npx skills add kengo006/alexandria --skill searcher
Clone the repo
git clone --depth 1 https://github.com/kengo006/alexandria

Made for: Claude Code, Codex.

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/skills/kengo006/alexandria/searcher/github.svg)](https://agentmods.dev/skills/kengo006/alexandria/searcher)
Your own site
<a href="https://agentmods.dev/skills/kengo006/alexandria/searcher"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/searcher/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.

agentmods 80×15 button for searcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/kengo006/alexandria/searcher"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/searcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00068 $0.00372
Opus 5 $0.00034 $0.00186
Sonnet 5 $0.00014 $0.00074
Haiku 4.5 $0.00007 $0.00037

Measured 10d ago against content hash 11cf0315338d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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/wrappers/searcher/SKILL.md · 22 lines

What it actually says

Searcher (wrapper)

Authority lives in the master file — this wrapper only loads it. (Normal operation: the Writer spawns this role via integration/agents/searcher.md; direct summoning is the fallback path.)

  1. Read governance/role-division.md.
  2. Read roles/searcher.md — source tiers, four-layer verification, both modes, failure modes.
  3. Orient: notes/vault-map.md, shared/search-patterns.md.

Digest of red lines (master wins):

  • Verbatim quotes / page numbers / emphasis come only from the source PDF at the page. Text layer, OCR, notes, semantic fragments: locate only.
  • Every quote passes four layers (correspondence / not-secondhand / settled position / entity attribution — the last flags rather than discards).
  • Present complete passages, never clipped stubs. Real printed page numbers.
  • Honest gaps ("needs extraction / pending verification") beat second-hand quotes, always.
  • Opposing positions: mandatory, never blank. None found ⇒ "searched, none found" plus the queries and scope you actually ran.
  • A missing page anchor is a locating problem, not an evidentiary one — markers come in several shapes; render the page and report the folio rather than downgrading the quote.
  • Read-only: no files written, nothing fixed — defects go into the errata section of the report.
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. 10d ago First seen · 22 lines · 68 tokens per session scan A 11cf0315338d

Subscribe to this mod's changes

searcher is a skill published in the GitHub repository kengo006/alexandria (5 stars, last pushed 17d ago), licensed MIT. It adds 68 tokens to every session and 372 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

socsci-paper-orchestrator

An orchestrator for writing Korean social-science research papers with a team of six specialized agents. Social science studies people, organizations, and society; a research paper presents a question, evidence, methods, and conclusions.

parkjui92/socsci-paper-kit · 384 tokens

citevahti-dev

Use when checking manuscript claims against evidence, assessing whether a citation actually supports what it is cited for, adding audited references to Zotero, generating a citation-integrity report, or when a researcher mentions claims, citations, PubMed, Zotero, PRISMA, blinded rating, or peer review of evidence.

heidihelena/citevahti · 66 tokens

citevahti-eval

Use when measuring or publishing CiteVahti's own accuracy — running the automatic claim-lexicon evaluation, checking it against its regression baseline, reasoning about how AI second-rater models are rated, or answering "how accurate is CiteVahti?". Follows ADR-0009's three evaluation objects (automatic lexicon eval…

heidihelena/citevahti · 97 tokens

citevahti-report

Use when packaging a completed CiteVahti audit for a journal, supervisor, or co-author — writing the methods-section paragraph that describes the claim-checking workflow, exporting the hash-chained audit trail, assembling an evidence appendix, or preparing a pre-submission integrity summary. Runs downstream of…

heidihelena/citevahti · 78 tokens

citevahti-review

Use when peer-reviewing or editing someone else's manuscript — checking whether each cited source supports the claim it is attached to, and producing a structured reviewer report of unsupported or overstated claims. Read-only, never writes to the author's Zotero and never rewrites their text. Uses the same blinded…

heidihelena/citevahti · 70 tokens

citevahti-support

Use when handling a CiteVahti user report — triaging a bug report or pilot-user email, updating the known-issues register, drafting a support reply, or deciding whether a report needs immediate escalation. Data-loss and false-verified reports escalate immediately. Maintainer-facing; mandatory from the first paying…

heidihelena/citevahti · 68 tokens