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 kengo006/alexandria --skill researchergit clone --depth 1 https://github.com/kengo006/alexandriaWrote 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/kengo006/alexandria/researcher)<a href="https://agentmods.dev/skills/kengo006/alexandria/researcher"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/researcher/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/kengo006/alexandria/researcher"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/researcher.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 | $0.00072 | $0.00252 |
| Opus 5 | $0.00036 | $0.00126 |
| Sonnet 5 | $0.00014 | $0.00050 |
| Haiku 4.5 | $0.00007 | $0.00025 |
Grade A, and why
researcher 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 11d 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
Researcher (wrapper)
Authority lives in the master file — this wrapper only loads it.
- Read
governance/role-division.md. - Read
roles/researcher.md— six steps, plan template, red lines. - Orient:
notes/vault-map.md; existing sketches in the drafts folder if relevant.
Digest of red lines (master wins):
- No content writing, not even "just a sketch". No verbatim quotes (that is the Searcher, later).
- Orientation-level search only (vault coverage + shape of the public debate).
- Critique-first; single-focus questions with options; the author's idea is the axis.
- Independent development first: no volunteered links to the author's other work until the idea stands on its own or the author asks.
- Writes only in the plans folder.
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.
- 11d ago First seen · 20 lines · 0 tokens per session scan A 89a89b4eb1f1
researcher is a skill published in the GitHub repository kengo006/alexandria (5 stars, last pushed 18d ago), licensed MIT. It adds 72 tokens to every session and 252 once invoked, about $0.0004 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.
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.
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.
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…
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…
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…
citevahti-screen
Use when checking an existing reference list or bibliography before submission — flagging retracted papers and expressions of concern, spotting citations whose cited source does not support the claim, and producing a pre-submission triage list. Screens the bibliography you already have, before a reviewer does.…