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 agentmods add skills/docxology/template/deep-researchnpx skills add docxology/template --skill deep-researchgit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/deep-research)<a href="https://agentmods.dev/skills/docxology/template/deep-research"><img src="https://agentmods.dev/badge/skills/docxology/template/deep-research.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00815 |
| Opus 5 | $0.00032 | $0.00407 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
template-deep-research 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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep research
Template-native research workflow. This skill routes to existing repository systems instead of running an autonomous external agent suite.
Natural invoke
- "Research this topic and build the source corpus"
- "Do a literature review with citation keys"
- "Fact-check these manuscript claims"
- "Guide me from vague research interest to answerable question"
- "Plan a systematic review with inclusion and exclusion criteria"
Inputs to confirm
- Research goal - question, audience, and expected deliverable.
- Mode - full, quick, lit-review, fact-check, guided, or systematic-review.
- Corpus source - arXiv, Crossref, local JSON corpus, provided papers, or project artifacts.
- Project target - if results feed a manuscript, use
docs/_generated/active_projects.md.
Workflow
- Question framing - turn vague topics into scoped research questions, explicit in/out boundaries, and search terms. Guided mode asks before converging.
- Source discovery - use
infrastructure.search.literatureand project-local corpora; record query, backend, date, DOI/arXiv IDs, and failures. - Source verification - resolve every candidate reference against Crossref / OpenAlex / arXiv with the deterministic reference-existence gate before it enters the corpus; reject
fabricated/mismatchrecords, surfaceunverifiable/uncheckedhonestly, and never invent unavailable bibliographic fields. This is the tier-0 anti-leakage step: flag the gap, do not hallucinate the citation. - Synthesis - hand off to literature-synthesis for per-paper notes, thematic clusters, contradictions, and gap analysis.
- Claim bridge - when research supports manuscript prose, create citekey-linked notes that manuscript-claim-verification can audit later.
Deliverables
- Research brief: question, scope, search strategy, corpus table, and evidence gaps.
- Literature synthesis with bracket-key citations and source-tier notes.
- Fact-check report: claim, source, verdict, uncertainty, action.
- For systematic review mode: protocol draft, inclusion/exclusion criteria, screening counts, and limitations.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 76 lines · 65 tokens per session scan A ad50fe206013
template-deep-research is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 815 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 2026-08-30.
Other skills, from other repositories
find-docs
Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service — even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training…
clinical-data-manager
Use when a task needs the judgment of a Clinical Data Manager — designing a CRF/eCRF and edit-check specification, writing or triaging a data query, planning database lock readiness, reconciling external data (lab, ePRO, IRT) against the clinical database, or reviewing a data management plan for a trial.
codeql-analysis
Run CodeQL queries to detect deep security vulnerabilities. Use when building CodeQL database, running language-specific queries, or validating results.
cloudbase-document-database-in-wechat-miniprogram
Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.
cloudbase-cli
CloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. Use when deploying cloud functions, CloudRun, storage, NoSQL/MySQL, static hosting, permissions, CORS/domains via tcb; for CI/CD and batch ops; when the user prefers CLI; or as the first-session fallback when CloudBase MCP tools are not…
mongodb-schema-design
MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one-to-many", "tree…