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/matthewdigiuseppe/mstack/lit-mapnpx skills add matthewdigiuseppe/MStack --skill lit-mapgit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWhat 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 | $0.00075 | $0.00938 |
| Opus 5 | $0.00037 | $0.00469 |
| Sonnet 5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
lit-map 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:lit-map
Stage: map Voice: systematic-reviewer
When to invoke
After /mstack:research-question returns a green or yellow verdict and you have a concrete claim. The lit-map exists to answer one question: what conversation is this paper joining, and where does it crack the consensus?
Procedure
-
Load context. Read
.mstack/research-question.md(the contribution sentence is the seed). -
Define the search. Produce a one-paragraph search strategy:
- 3–5 keyword combinations.
- 2–3 authors whose work is most directly engaged.
- Time window (typically last 10 years, plus the foundational older papers).
- Venues (top-3 IPE / political science journals plus working-paper repositories like SSRN, NBER, OSF). Get user sign-off before searching.
-
Search.
- Use WebSearch for keyword + author scans.
- Use WebFetch (or, if available, a Google Scholar / Semantic Scholar MCP) to pull abstracts and citation counts for top hits.
- Build a candidate set of 20–40 papers.
-
Triage. Classify each paper into:
- Foundation (3–5): the canonical works the conversation rests on. Must-cite or you look unread.
- Frontier (5–10): recent work in active conversation with the paper's claim. Engage explicitly.
- Adjacent (5–10): related but on a different question. Cite once, don't engage at length.
- Discard (the rest): noted in the file, not engaged.
-
Map the consensus. For Foundation + Frontier, produce a one-paragraph synthesis:
- What does the consensus believe?
- Where does it crack? What is contested?
- What does the canonical work not answer?
-
Locate the gap. State, in one paragraph, where the user's project fits:
- Which paper(s) does it most directly engage?
- What does it add that they don't have?
- Which hostile reviewer would object, and why?
-
Stage
refs.bibentries. For every Foundation + Frontier paper, produce a BibTeX entry and append topaper/refs.bib(deduped by key). Do not invent fields — if a field (e.g., page numbers) isn't available, leave it blank with a% TODOcomment.
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 · 75 lines · 75 tokens per session scan A 6c19f3a1b139
lit-map is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 938 once invoked, about $0.0004 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
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…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.