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 jxtse/scientific-research-skills --skill related-work-surveygit clone --depth 1 https://github.com/jxtse/scientific-research-skillsWrote 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/jxtse/scientific-research-skills/related-work-survey)<a href="https://agentmods.dev/skills/jxtse/scientific-research-skills/related-work-survey"><img src="https://agentmods.dev/badge/skills/jxtse/scientific-research-skills/related-work-survey/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/jxtse/scientific-research-skills/related-work-survey"><img src="https://agentmods.dev/badge/skills/jxtse/scientific-research-skills/related-work-survey.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 | $0.00145 | $0.00954 |
| Opus 5 | $0.00072 | $0.00477 |
| Sonnet 5 | $0.00029 | $0.00191 |
| Haiku 4.5 | $0.00015 | $0.00095 |
Grade A, and why
related-work-survey 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 13d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Related Work Survey
Systematic literature survey for positioning a research contribution.
When to Use
- User starts a new research project and needs landscape understanding
- User asks "what's been done on X?"
- User needs to write a related work section
- User wants to identify the gap their work fills
Workflow
Step 1: Define the Research Question
Work with the user to pin down:
- Core question: What specific problem are we solving?
- Key concepts: What are the 3-5 key terms/concepts?
- Scope boundaries: What's in scope vs. adjacent but out of scope?
Step 2: Identify Survey Dimensions
Every research topic sits at an intersection of multiple dimensions. Identify 2-4 axes:
Example for "Neural-Symbolic Decomposition in LLM Agents":
- Axis 1: Neuro-symbolic integration approaches
- Axis 2: LLM agent architectures (harness, scaffolding)
- Axis 3: Adaptive/metacognitive planning
- Axis 4: Text analysis at scale (specific application)
Step 3: Search Each Dimension
For each axis, use literature-search skill with targeted queries:
Axis 1 → "neuro-symbolic integration LLM reasoning 2024 2025"
Axis 2 → "LLM agent harness scaffolding architecture survey"
Axis 3 → "metacognitive planning adaptive tool use LLM"
Axis 4 → "large scale text analysis LLM code generation quality"
Collect 10-20 papers per axis, then deduplicate across axes.
Step 4: Build the Taxonomy
Organize papers into a structured taxonomy:
## Related Work Taxonomy
### 1. Neuro-Symbolic Integration
1.1 Neural reasoning with symbolic verification
1.2 Symbolic planning with neural execution
1.3 Adaptive decomposition (our focus)
### 2. LLM Agent Architecture
2.1 Harness engineering
2.2 Self-evolving agents
2.3 Meta-Harness optimization
### 3. ...
Step 5: Identify the Gap
The gap is where your work lives — the intersection that no existing paper covers:
Paper A does X but not Y.
Paper B does Y but not X.
We do both X and Y, connected by Z.
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.
- 13d ago First seen · 129 lines · 145 tokens per session scan A 62b897cfa124
related-work-survey is a skill published in the GitHub repository jxtse/scientific-research-skills (68 stars, last pushed 3mo ago), licensed MIT. It adds 145 tokens to every session and 954 once invoked, about $0.0007 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
paper-fetch
Retrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly…
benchmark-archaeology
Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.
bias-detection
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
competitive-intelligence
Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.
claim-analysis
Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.
adversarial-persona
Strategy: Role-play attacks from hostile personas — competing lab researcher, hostile reviewer, funding skeptic, domain outsider — each with distinct attack motivations and blind spots.