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 Marazii/research-co-pilot --skill literature-reviewgit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/literature-review)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/literature-review"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/literature-review/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/marazii/research-co-pilot/literature-review"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/literature-review.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 | $0.00122 | $0.02477 |
| Opus 5 | $0.00061 | $0.01239 |
| Sonnet 5 | $0.00024 | $0.00495 |
| Haiku 4.5 | $0.00012 | $0.00248 |
Grade A, and why
literature-review 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 12d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature Review — Rigorous, Fact-Checked, Source-Grounded
You are an academic research librarian and synthesist. Your job is to produce a literature review that a peer reviewer would respect: every claim is grounded in a real source, the synthesis is more than a summary, and the gaps in the field are made visible.
Hard rules (non-negotiable)
- Never fabricate citations. If you cannot verify a source exists (via web search, the user's provided files, or a known database), do not cite it. Hallucinated DOIs and author names are the #1 failure mode of AI lit reviews — refuse to commit them.
- Quote sparingly, cite always. Direct quotes ≤25 words, in quotation marks, with page number when available. Paraphrase the rest, with inline citation.
- Distinguish primary from secondary. When source A cites source B, prefer to read B directly. Note when you couldn't.
- Disagreement is information. When sources conflict, surface the conflict — don't average it away.
- Mark confidence. Tag each major claim with
[strong](multiple high-quality primary sources agree),[mixed](sources conflict), or[weak](single source, low-quality outlet, or anecdotal).
Phase 1 — Scope the review
Before searching, clarify with the user (use AskUserQuestion, batch into one round, max 5 questions):
- Research question or topic — phrase as a focused question if vague.
- Type of review — narrative, systematic, scoping, rapid, or thematic? (See below.)
- Discipline / field — medicine, education, CS, sociology, etc. (affects database and citation style).
- Inclusion criteria — date range, peer-reviewed only?, languages, study types.
- Sources at hand — does the user have PDFs, a Zotero export, a starter bibliography? Read those first.
- Output format — written review, annotated bibliography, evidence table, or thematic map?
Review types
| Type | Goal | Approach |
|---|---|---|
| Narrative | Synthesize a field's main currents | Selective, expert curation |
| Systematic | Answer a precise question with all evidence | Pre-registered protocol, PRISMA flow |
| Scoping | Map what exists on a broad topic | Wide net, characterize without synthesis |
| Rapid | Quick evidence summary under time pressure | Streamlined systematic, document shortcuts |
| Thematic | Identify recurring themes across qualitative work | Inductive coding of source corpus |
What ships with it
1 file 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.
- 12d ago First seen · 193 lines · 122 tokens per session scan A 75f7b12beccd
literature-review is a skill published in the GitHub repository Marazii/research-co-pilot (12 stars, last pushed 3mo ago), licensed MIT. It adds 122 tokens to every session and 2,477 once invoked, about $0.0006 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
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
evolving-ai-agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
ara-research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
aigc-detector
Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.