literature-evidence-mapping

literature-evidence-mapping is a skill for Claude Code, Codex from BingHanOfUESTC/open_agent_team. It costs 35 tokens per session (860 once invoked), scanned A, original, MIT.

A research workflow for finding papers, reading them closely, checking citations, and recording evidence. It is designed for building a reliable map of existing academic work.

In plain words
What is it for?
Use it to plan literature searches, screen and organize papers, follow related citations, identify recent or negative results, and collect evidence for a research paper.
Why use it?
It reduces the chance of missing important studies or making claims without support by requiring search plans, paper inventories, evidence cards, and limitation checks.

Skill for Claude CodeCodex

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

Good fit Use it to plan literature searches, screen and organize papers, follow related citations, identify recent or negative results, and collect evidence for a research paper.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/binghanofuestc/open_agent_team/literature-evidence-mapping
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 BingHanOfUESTC/open_agent_team --skill literature-evidence-mapping
Clone the repo
git clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_team

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 literature-evidence-mapping

README.md
[![agentmods](https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/literature-evidence-mapping/github.svg)](https://agentmods.dev/skills/binghanofuestc/open_agent_team/literature-evidence-mapping)
Your own site
<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/literature-evidence-mapping"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/literature-evidence-mapping/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 literature-evidence-mapping

Your own site · 80×15
<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/literature-evidence-mapping"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/literature-evidence-mapping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00035 $0.00860
Opus 5 $0.00017 $0.00430
Sonnet 5 $0.00007 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 11d ago against content hash c64b3c1473dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

literature-evidence-mapping 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.

teams/auto_research_team/skills/literature-evidence-mapping/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Literature Evidence Mapping

This skill turns search results into research-grade evidence. It should be used before ideation and again before final paper writing.


1. Search Plan

Write:

research_workspace/literature/search_plan.md

Include:

research question
inclusion criteria
exclusion criteria
search queries
venues and indexes
date window
target benchmark or dataset names

Use recursive search when the field is unclear or the first pass returns shallow coverage:

breadth pass: collect diverse candidate papers
depth pass: follow citations, authors, code links, benchmarks
gap pass: search directly for failure modes and limitations
recency pass: search the latest arXiv/OpenReview/venue/Papers With Code entries

Default depth floor:

screen 30-60 candidate papers
include 15-30 relevant papers
deep-read 8-12 key papers
collect at least 5 recent papers from the last 24 months when available
collect at least 3 limitation/negative-result sources

2. Paper Inventory

Maintain:

research_workspace/literature/paper_inventory.tsv

Columns:

id
canonical_key
title
authors
year
venue
url
code_url
data_url
task
method_family
benchmark
result_claim
evidence_level
source_pass
why_relevant
limitations_signal
status

Status values:

candidate
included
excluded
deep_read
baseline_source
idea_source
citation_only

3. Evidence Card

For every key paper, write a card under:

research_workspace/literature/cards/<paper_id>.md

Template:

# <paper title>

- Citation:
- Source URL:
- Code/Data:
- Problem:
- Method:
- Key assumptions:
- Experiments:
- Reported results:
- Limitations stated by authors:
- Limitations inferred by team:
- Relevance to current research:
- What can be reused:
- What should not be assumed:
- Citation key:
- Paper section/table/figure anchors:
- Related-work bucket:
- Claims allowed in paper:
- Claims not supported:

Deep-read cards must come from full paper text whenever possible. If only abstract or metadata was available, mark the card as abstract_only and do not use it for method details, result comparisons, or limitations beyond the abstract text.

Read the full file on GitHub · 183 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. 11d ago First seen · 183 lines · 35 tokens per session scan A c64b3c1473dd

Subscribe to this mod's changes

literature-evidence-mapping is a skill published in the GitHub repository BingHanOfUESTC/open_agent_team (106 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 860 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 2026-08-30.

Related

Other skills, from other repositories