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 yqi96/warranted --skill literature-surveygit clone --depth 1 https://github.com/yqi96/warrantedWrote 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/yqi96/warranted/literature-survey)<a href="https://agentmods.dev/skills/yqi96/warranted/literature-survey"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/literature-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/yqi96/warranted/literature-survey"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/literature-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 | $0.00052 | $0.10914 |
| Opus 5 | $0.00026 | $0.05457 |
| Sonnet 5 | $0.00010 | $0.02183 |
| Haiku 4.5 | $0.00005 | $0.01091 |
Grade A, and why
literature-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 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.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phases
| Phase | Ends when | Graph state produced |
|---|---|---|
| 1. Scope | The protocol Statement exists | One meta:protocol Statement holding question, criteria, planned search |
| 2. Screen | No row in screening.csv is still PENDING, and every INCLUDED row has a paper: tag |
Candidate ledger on disk; tag ledger of inclusions; protocol Statement updated with actual counts |
| 3. Extract | Every INCLUDED tag has statements or a terminal status |
Pending Statements carrying only paper: tags |
| 4. Classify | No Statement has a paper: tag without a theme: tag |
Converged theme vocabulary; every Statement classified |
| 5. Synthesize | Every Claim has a verdict — or is proposed for a reason written into its Warrant — every theme either carries a Rebuttal or says in its Warrant why its evidence is consistent, and compiles are fresh |
Multi-root DAG; everything attached to it verified |
Build no Warrants before phase 5. Adding a Ground to a Warrant invalidates that Claim and every Claim above it, so any argument structure built during ingestion gets recompiled on every subsequent batch.
Phases 3 and 4 alternate. Run phase 4 every 3–5 extraction batches — never extract everything and classify at the end. A taxonomy built once, at the end, is dominated by whatever you read last.
Phase 1 — Scope
Before any search, create the protocol Statement:
create_tags([
{name: "meta:protocol", description: "Survey protocol and screening record"},
{name: "meta:conflict", description: "Statement conflicts with another finding; resolve in phase 5"},
])
create_statement(
source="observed", verification="pending", tags=["meta:protocol"],
content="<research question> | Inclusion: <criteria> | Exclusion: <criteria> | Planned search: <venues, years, queries>"
)
This node is not bookkeeping. It becomes the Backing of the coverage Warrant in phase 5, it is the only place the survey's scope survives a lost session, and it is the text every screening subagent is given verbatim. Write the criteria in it in full — not a summary of them. A criterion you compress here is a criterion the screeners never receive.
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 · 364 lines · 52 tokens per session scan A 21570482cf00
literature-survey is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 10,914 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 2026-08-31.
Other skills, from other repositories
argument-mapping
Use this Skill to extract and visualize argument structure: Toulmin reconstruction, support/attack graph, circularity detection, argument scheme classification, and NLP-based premise extraction.
proof-checker
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
citation-audit
A verification tool for checking whether a paper's bibliography entries are real, correctly described, and used to support the claims they accompany.
idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
research-refine
A research-planning guide that turns a broad research idea into a specific method and a small validation plan.