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 bayeslabs-rsi/Svatah --skill literaturegit clone --depth 1 https://github.com/bayeslabs-rsi/SvatahWrote 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/bayeslabs-rsi/svatah/literature)<a href="https://agentmods.dev/skills/bayeslabs-rsi/svatah/literature"><img src="https://agentmods.dev/badge/skills/bayeslabs-rsi/svatah/literature/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/bayeslabs-rsi/svatah/literature"><img src="https://agentmods.dev/badge/skills/bayeslabs-rsi/svatah/literature.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 | $0.00027 | $0.00407 |
| Opus 5 | $0.00014 | $0.00204 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
literature 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.
What it actually says
Literature Curation
Svatah literature is a run-start input, not an optimization-loop activity.
Initial Curation
Run this exactly once after the benchmark baseline is committed and
.sva/project.md describes the task, inputs, primary metric, constraints, and
baseline:
sva literature curate --repo-root .
The command builds a typed project profile, issues one bounded query to each configured academic provider, rejects unrelated sources, synthesizes concrete source-grounded method cards, and freezes the result for the active run. Resuming the run reuses the same snapshot.
Read-Only Inspection
sva literature status --repo-root .
sva literature cards --repo-root . --limit 3
sva literature cards --repo-root . --query "<typed task or mechanism>" --limit 3
These commands never access the network. Round plans and subagent briefs may use only card IDs from this frozen snapshot.
Manual Revision
Only an operator may replace a frozen snapshot, and only when the project or benchmark contract materially changed:
sva literature curate --repo-root . --refresh --reason "<project contract change>"
This creates a new revision and preserves the previous revision. Advisors, critics, recovery rounds, plateau handling, and subagents must never invoke a refresh automatically.
Rules
- Do not invoke provider adapters directly or construct an ad hoc query.
- Do not turn hypotheses, critic feedback, experiment IDs, or planner labels into literature queries.
- Do not claim that an abstract proves an exact implementation.
- A literature-backed experiment must reference a valid frozen method-card ID.
- If curation is empty or unavailable, continue without literature. Do not retry automatically.
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 · 59 lines · 27 tokens per session scan A 291b07f0a348
literature is a skill published in the GitHub repository bayeslabs-rsi/Svatah (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 407 once invoked, about $0.0001 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
proof-checker
A rigorous proof-checking and repair skill for LaTeX mathematics. LaTeX is a text format commonly used to write mathematical documents.
paper-illustration
A tool for creating academic-paper illustrations such as architecture diagrams and method figures with Gemini image generation and Claude-guided revisions.
paper-navigator
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), and read with structured analysis (3-level strategy). Use when: finding papers, reading a paper, related work, citation…
paper-write
A section-by-section LaTeX drafting workflow based on a paper outline. LaTeX is a text-based system commonly used to format academic papers.
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
experiment-pipeline
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…