Borrowing it
Nothing to install: this file belongs to aspenkit/aspens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aspenkit/aspens/main/.agents/skills/import-graph/SKILL.mdgit clone --depth 1 https://github.com/aspenkit/aspensWrote 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/aspenkit/aspens/import-graph)<a href="https://agentmods.dev/skills/aspenkit/aspens/import-graph"><img src="https://agentmods.dev/badge/skills/aspenkit/aspens/import-graph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aspenkit/aspens/import-graph"><img src="https://agentmods.dev/badge/skills/aspenkit/aspens/import-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00026 | $0.01076 |
| Opus 5.5 | $0.00010 | $0.00430 |
| Sonnet 5.5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
import-graph 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are working on the import graph system — static analysis that parses JS/TS and Python source files to produce dependency graphs, plus persistence/query layers for runtime use.
Domain purpose
The graph turns raw source into a queryable map of "what depends on what" so other aspens features (doc-init, doc-sync, doc-impact, the graph context hook) can rank files by importance, surface hubs, detect domain clusters, and inject just the relevant neighborhood into prompts. It is the substrate that makes context generation deterministic and code-aware rather than guess-based.
Key Concepts
graph-builder.js — buildRepoGraph(repoPath, languages?) runs a 9-step pipeline:
- Walk source files → 2. Parse imports → 3. Reverse edges → 4. Git churn → 5. Per-file metrics → 6. Priority ranking → 7. Hub detection → 8. Domain clustering → 9. Hotspots
graph-persistence.js — Persistence and query layer:
serializeGraph()converts raw graph to indexed format (O(1) lookups, file→cluster mapping)persistGraphArtifacts(repoPath, rawGraph, options?)writes.claude/graph.json+.claude/code-map.md+.claude/graph-index.json+ auto-gitignores them. Target-aware: ifoptions.target.supportsGraph === false, returns serialized data without writing files.extractSubgraph(graph, filePaths)returns 1-hop neighborhood of mentioned files + relevant hubs/hotspots/clustersformatNavigationContext(subgraph)renders compact markdown (~50 line budget) for prompt injectionextractFileReferences(prompt, graph)tiered extraction: explicit paths → bare filenames → cluster keywordsgenerateCodeMap()/writeCodeMap()standalone overview for graph hook consumption — emits a Domain clusters block (viaformatDomainClusters) and framework entry points only; cross-domain coupling, hotspots, and the totals/date footer are intentionally omitted because they churn on every syncformatDomainClusters(clusters, files)— exported helper that renders the canonical Domain clusters block: clusters are merged by label, single-file clusters dropped, files per cluster capped at 5 and sorted byfanIndesc then path asc for sync stability; no per-cluster(N files)countsgenerateGraphIndex()/saveGraphIndex()tiny inverted index (export names → files, hub basenames, cluster labels)
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.
- 1mo ago First seen · 61 lines · 26 tokens per session scan A afe35929d59c
import-graph is a skill published in the GitHub repository aspenkit/aspens (103 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,076 once invoked, about $0.0001 per session on Opus 5.5. 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
jev
Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".
sw-jev
Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".
docverity
Check whether a project's documentation still matches its code, and report stale or wrong claims with suggested fixes. Use this after editing, renaming, moving, or deleting source files, CLI flags, environment variables, or functions, to catch docs you may have just made inaccurate; when the user asks whether the…
vg
Query the local code graph (vg) for structure, impact, and navigation instead of grepping/reading many files.
execute-use-case
Walk one path on a use-case tree in docs/hops.md: Input → matching Branches → Output. Default cheap path. Use when implementing or debugging a known flow — not when mapping a new one.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.