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/learningmatter-mit/atomisticskills/general-deep-researchnpx skills add learningmatter-mit/AtomisticSkills --skill general-deep-researchgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWhat 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 | $0.00024 | $0.00945 |
| Opus 5 | $0.00012 | $0.00473 |
| Sonnet 5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
general-deep-research 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Goal
To perform an in-depth, iterative, and comprehensive literature and web research campaign to answer complex scientific questions (e.g., "What are the synthesis methods and solid-state electrolyte performance of LiInCl3?"). This skill produces a high-quality, synthesized research report with citations, significantly exceeding the depth of a single simple literature query.
Instructions
When the user requests deep research on a topic, the agent MUST follow this multi-step iterative protocol. Do not implement this as a python script, but rather execute these steps logically using your own tool-calling capabilities.
Step 1: Query Formulation & Planning
Break down the user's broad research topic into 3-5 specific sub-queries.
CRITICAL: You must try different permutations and synonyms for the material or topic. For example, if the topic is LiInCl3, your queries must include variations like LiInCl3, Li-In-Cl, Lithium Indium Chloride, Li3InCl6, etc., to ensure no literature is missed.
Create a rough outline for the final research report in your task plan.
Step 2: Iterative Literature Search
For each sub-query, use the mcp_base_search_literature tool to search the OpenAlex database. Always set download=True to attempt downloading the full text of discovered papers.
mcp_base_search_literature(
query="Lithium Indium Chloride ionic conductivity",
limit=50,
download=True
)
CRITICAL: You must NOT rely solely on the literature search tool. You must ALSO perform a general web search using the search_web tool for all your queries. This captures recent publications, patents, reviews, and data that OpenAlex might miss.
search_web(
query="Li-In-Cl solid state electrolyte review"
)
Step 3: Information Extraction & Synthesis
Do not just list papers. You must read the content (or the provided summaries/full texts from the MCP tool). Extract specific numbers, methodologies, and limitations (e.g., "Conductivity is 1.2 mS/cm at RT", "Synthesized via mechanochemical milling followed by annealing at 250C").
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.
- 2d ago First seen · 85 lines · 24 tokens per session scan A c4ac0838ce22
general-deep-research is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (154 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 945 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 2026-08-30.
Other skills, from other repositories
algebra
Solve equations, simplify expressions, and factor polynomials. Use when doing algebra homework, checking proofs, or plotting functions.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…