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 skills add KimHG1995/ts-graph-tools --skill ts-graphgit clone --depth 1 https://github.com/KimHG1995/ts-graph-toolsWrote 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/kimhg1995/ts-graph-tools/ts-graph)<a href="https://agentmods.dev/skills/kimhg1995/ts-graph-tools/ts-graph"><img src="https://agentmods.dev/badge/skills/kimhg1995/ts-graph-tools/ts-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/kimhg1995/ts-graph-tools/ts-graph"><img src="https://agentmods.dev/badge/skills/kimhg1995/ts-graph-tools/ts-graph.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00650 |
| Opus 5.5 | $0.00012 | $0.00260 |
| Sonnet 5.5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
ts-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 13d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript code graph
Use the available inspect_typescript_graph MCP tool to narrow structural
TypeScript questions before reading whole files. This skill supplies a workflow;
it does not install or register the server.
Select the project
Use the server registered for the user's target repository. When several servers expose the tool, use registration and working-directory evidence to select one; the server name alone does not establish its target. Check the returned project on the first useful query. If it differs, select the correct server before using the result. If the target remains ambiguous, ask for the missing project context.
If the tool is unavailable or fails, use scoped source searches and reads and state that limitation. Do not change dependencies or MCP settings just to answer a code question.
Choose the smallest useful request
Use the connected tool's schema for the request envelope and supported inputs. Keep required rationale fields brief and task-focused.
| Question | Request |
|---|---|
| Architecture or a runtime-flow tour | tour |
| Unknown execution starting point | entrypoints |
| Symbol location or ambiguous name | lookup |
| Callers / callees | trace with reverse / forward |
| Path from A to B | trace with from and to |
| Change impact in the current source | trace with direction: impact |
| Signatures, members, interface implementations | details |
| Folder layers or project shape | overview |
Reuse returned symbol handles for follow-up requests. For example, to answer
"Who calls OrderService.create?", select the project's server and request a
reverse execution trace; use lookup first if the symbol is ambiguous.
Use the evidence within its limits
Answer relationship questions from returned symbols, edges, and source spans,
citing file locations. Avoid rereading whole files merely to repeat a relationship
the graph already supplies. Use audit, next, and truncation information to
decide whether to answer, make a focused follow-up, or inspect source.
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.
- 13d ago First seen · 67 lines · 30 tokens per session scan A e1e505d5c1a1
ts-graph is a skill published in the GitHub repository KimHG1995/ts-graph-tools (0 stars, last pushed 14d ago), licensed Unlicense. It adds 30 tokens to every session and 650 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 2026-10-02.
Other skills, from other repositories
cli-wiring
Bug class: Commands implemented in packages/squad-cli/src/cli/commands/ but never routed in cli-entry.ts.
agents-sdk-typescript-debugging
Use when troubleshooting an agent built with the Microsoft Agents SDK (@microsoft/agents-hosting and related packages). Trigger on any of these symptoms: build or TypeScript errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, .env configuration problems, Azure AD…
config
How to author a kubb.config.ts and pick the right @kubb/plugin- packages when generating TypeScript from an OpenAPI/Swagger spec. Use whenever setting up Kubb, adding a generator, or debugging codegen output.
node-modules-inspector
Inspects a project's installed nodemodules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate…
mintlify-api
Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.
angular
Use when building, refactoring, or debugging Angular (v20/21+): standalone components, signals, zoneless change detection, @if/@for/@defer control flow, inject() DI, resource()/httpResource(), RxJS interop, NgRx SignalStore, ng CLI. NOT React (that is react), NOT Next.js (that is nextjs), NOT a TypeScript language…