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 agentmods add skills/kdevos12/alkyl/lit-rescuenpx skills add Kdevos12/ALKYL --skill lit-rescuegit clone --depth 1 https://github.com/Kdevos12/ALKYLWrote 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/kdevos12/alkyl/lit-rescue)<a href="https://agentmods.dev/skills/kdevos12/alkyl/lit-rescue"><img src="https://agentmods.dev/badge/skills/kdevos12/alkyl/lit-rescue.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01612 |
| Opus 5 | $0.00028 | $0.00806 |
| Sonnet 5 | $0.00011 | $0.00322 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
lit-rescue 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lit-Rescue — Literature-Grounded Problem Solving
When to invoke this skill:
- No confident answer exists from training knowledge
- The problem involves a specific algorithm, parameter, protocol, or library behavior that could be misremembered
- Previous attempts at solving the problem have been inconsistent or failed
- The question is novel, niche, or at the edge of a domain
- The user is debugging something that "shouldn't happen"
Rule: If there is >20% chance the answer could be fabricated or outdated → invoke this skill first.
Step 1 — Classify the Problem
Identify the query type before formulating search queries:
| Type | Keywords | Primary MCP |
|---|---|---|
| METHOD | "which algorithm", "best approach for", "how to compute X" | Perplexity → bioRxiv |
| PARAM | "what value for", "typical hyperparameters", "threshold for" | Perplexity → PubMed |
| BUG | "why does X fail", "unexpected behavior", "error in library" | Perplexity only |
| THEORY | "physical basis of", "why does X work", "derivation" | PubMed → bioRxiv |
| PROTOCOL | "standard procedure", "step-by-step for", "pipeline for" | bioRxiv → PubMed |
| BENCHMARK | "comparison of methods", "state of the art for", "which is better" | bioRxiv → PubMed |
| DOMAIN | highly specialized jargon or niche subfield | Perplexity → PubMed |
Multiple types can apply — activate each relevant search.
Step 2 — Formulate Queries
Load references/perplexity-prompts.md if Perplexity MCP is available.
Otherwise, construct queries following these principles:
- Be maximally specific — include library name + version, domain, and exact task
- Ask for citations — request DOIs, paper titles, or package documentation references
- Anchor to peer-reviewed content — explicitly exclude opinion/blog content for scientific questions
- Specify recency — for fast-moving fields, constrain to last 2–3 years
Step 3 — Execute Search Waterfall
What ships with it
2 files 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.
- 4d ago First seen · 184 lines · 57 tokens per session scan A 8129b0005be9
lit-rescue is a skill published in the GitHub repository Kdevos12/ALKYL (6 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 1,612 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
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
molecular-optimization
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).
admet-reasoning
Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.