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/microsoft/hve-core/feasibilitynpx skills add microsoft/hve-core --skill feasibilitygit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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 | $0.00054 | $0.01520 |
| Opus 5 | $0.00027 | $0.00760 |
| Sonnet 5 | $0.00011 | $0.00304 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
feasibility 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 3d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data and ML Feasibility Workflow
Goal
Produce one durable Markdown feasibility study that remains useful to people and can be consumed later by a Functional Planner. One constrained YAML block owns machine facts; narrative sections preserve evidence, interpretation, and context.
Flow
- Confirm the proposed outcome, decision boundary, study scope, and durable output path.
- Allocate UUIDv4 URNs for the study concept, study revision, each item concept, each item revision, and each relation. Never derive identity from a title, class, path, or content.
- Capture candidate capabilities, constraints, assumptions, findings, risks, dependencies, decisions, evidence, gaps, and non-goals. Preserve uncertainty and source-authored criteria without promoting every item to a requirement.
- Record lifecycle and provenance. Reclassification keeps conceptual identity and creates a new revision. Split, merge, derivation, withdrawal, and supersession retain explicit lineage.
- Write or update the single named
FEASIBILITY-STUDY-INTERCHANGEYAML block. Narrative can explain machine facts but cannot redefine them. - Validate constrained YAML, JSON Schema 2020-12 structure, semantic closure, revision lineage, tombstones, and narrative anchors with
scripts/validate_feasibility.py. - Present the recommendation and unresolved review gaps. Preserve the study as read-only evidence for downstream consumers.
- After the study is final, emit the sibling feasibility-to-PRD handoff described in feasibility-to-prd-handoff.md. Regenerate it after any material study revision.
Inputs
- Problem definition, desired outcome, and decision the study must support
- Data access, discovery, architecture, exploration, preprocessing, and experiment evidence
- Source-authored acceptance criteria, when known
- Risk, privacy, Responsible AI, performance, and operational evidence
- Prior study revision and item identity registry, when revising an existing study
What ships with it
19 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.
- assets/feasibility-study-interchange-1.0.0.schema.json 5.9 KB
- examples/invalid-fixtures.md 1.6 KB
- examples/valid-study.md 5.3 KB
- pyproject.toml 701 B
- references/feasibility-to-prd-handoff.md 9.7 KB
- references/interchange-profile.md 7.3 KB
- references/provenance.md 2.9 KB
- references/standards-crosswalk.md 3.9 KB
- scripts/validate_feasibility.py 21 KB runs code
- templates/feasibility-study.md 2.6 KB
- tests/corpus/0_valid_profile 130 B
- tests/corpus/1_anchor_alias 143 B
- tests/corpus/2_duplicate_key 129 B
- tests/corpus/3_unterminated_block 66 B
- tests/corpus/4_no_block 26 B
- tests/corpus/README.md 1.3 KB
- tests/fuzz_harness.py 1.2 KB runs code
- tests/test_validate_feasibility.py 17 KB runs code
- uv.lock 108 KB
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.
- 3d ago First seen · 86 lines · 54 tokens per session scan A d6e65fce6e80
feasibility is a skill published in the GitHub repository microsoft/hve-core (1,411 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,520 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 2026-08-30.
Other skills, from other repositories
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
geniml
Use Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.
cellxgene-census
Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across…
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).