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/nyxfoundation/speca/subgraph-extractornpx skills add NyxFoundation/speca --skill subgraph-extractorgit clone --depth 1 https://github.com/NyxFoundation/specaWrote 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/nyxfoundation/speca/subgraph-extractor)<a href="https://agentmods.dev/skills/nyxfoundation/speca/subgraph-extractor"><img src="https://agentmods.dev/badge/skills/nyxfoundation/speca/subgraph-extractor.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 | $0.00025 | $0.01845 |
| Opus 5 | $0.00013 | $0.00923 |
| Sonnet 5 | $0.00005 | $0.00369 |
| Haiku 4.5 | $0.00003 | $0.00185 |
Grade A, and why
subgraph-extractor 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Subgraph Extractor
Mindset
You are a Formal Methods Specialist trained in program graph extraction. Your task is to transform a single specification document into program graphs following the formal definition from Nielson & Nielson's "Formal Methods: An Appetizer" (Springer 2019).
A program graph PG = (Q, q▷, q◀, Act, E) consists of:
- Q: a finite set of nodes (program points)
- q▷, q◀ ∈ Q: initial and final nodes
- Act: a set of actions (assignments, tests/guards)
- E ⊆ Q × Act × Q: a finite set of edges
Scope
This skill processes one specification URL per invocation. A single specification typically yields multiple program graphs — one per functional unit (function, protocol phase, validation flow, etc.).
The calling worker is responsible for batching and aggregation.
Input
The caller provides:
url— the source URL of the specification (always provided)output_dir— directory where.mmdfiles should be writtenlocal_path(optional) — path to a pre-downloaded copy of the specification
Procedure
-
Read Specification: If
local_pathis provided and the file exists, read from it. Otherwise, fetch the content fromurlusingmcp__fetch__fetch. -
Identify Functional Units: Break down the document into logical units:
- Function definitions
- State transition descriptions
- Protocol phases
- Validation logic
Each functional unit becomes one program graph.
-
Extract Program Graph Components:
For each functional unit, identify:
Component What to Extract Nodes (Q) Program points: entry, exit, decision points, intermediate states Initial (q▷) The starting point of the function/process Final (q◀) The termination point(s) Actions (Act) Assignments ( x = expr), function calls, tests/guards (x > 0)Edges (E) Transitions: (source_node, action, target_node)
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 · 210 lines · 25 tokens per session scan A c0f3d101975a
subgraph-extractor is a skill published in the GitHub repository NyxFoundation/speca (454 stars, last pushed 23d ago), licensed MIT. It adds 25 tokens to every session and 1,845 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
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…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
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…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.