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 itaisatati/tsc-trace-analyzer --skill tsc-trace-analyzergit clone --depth 1 https://github.com/itaisatati/tsc-trace-analyzerWrote 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/itaisatati/tsc-trace-analyzer/tsc-trace-analyzer)<a href="https://agentmods.dev/skills/itaisatati/tsc-trace-analyzer/tsc-trace-analyzer"><img src="https://agentmods.dev/badge/skills/itaisatati/tsc-trace-analyzer/tsc-trace-analyzer/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/itaisatati/tsc-trace-analyzer/tsc-trace-analyzer"><img src="https://agentmods.dev/badge/skills/itaisatati/tsc-trace-analyzer/tsc-trace-analyzer.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 | $0.00062 | $0.03690 |
| Opus 5.5 | $0.00025 | $0.01476 |
| Sonnet 5.5 | $0.00012 | $0.00738 |
| Haiku 4.5 | $0.00006 | $0.00369 |
Grade C, and why
tsc-trace-analyzer scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/tsc-trace-analyzer-trace /tmp/tsc-trace-analyzer-emit How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tsc-trace-analyzer
Run tsc --generateTrace on a TypeScript project, parse the resulting trace files, identify compilation bottlenecks, and suggest concrete code fixes.
When to use
Use this skill whenever the user complains that the TypeScript compiler or compilation is slow, or when they want to investigate where tsc is spending time. Triggers include — but are not limited to — any of the following:
- "The TypeScript compiler is slow" / "tsc is slow" / "compilation is slow"
- "My TypeScript build is slow" / "the build takes forever"
- "Type checking is slow" / "type checking takes forever" / "tsc takes forever"
- "Why is my TypeScript project so slow to compile?"
- "How do I make tsc faster?" / "How do I speed up TypeScript?"
- "Find TypeScript performance bottlenecks" / "Find type-checking hotspots"
- "Profile the TypeScript compiler" / "profile tsc"
- Any mention of
--generateTrace,trace.json,types.json, "tsc trace", or "TypeScript tracing" tscis crashing with a JavaScript heap out-of-memory error and the user wants to understand or fix it- The user wants to know what the TypeScript compiler is spending its time on
- The user asks for help reducing TypeScript compile times, build times, or CI times caused by
tsc
Also use it proactively if the user shares a slow tsc build log, a long type-checking duration, or asks for advice on TypeScript performance optimization.
Instructions
Follow these steps in order:
Step 1: Find tsconfig.json
Search for tsconfig.json files in the project:
- Use Glob to find
**/tsconfig.jsonfiles, excludingnode_modules - If exactly one is found, use it
- If multiple are found, pick by this priority order:
- Root
tsconfig.jsonat the project root — use it if present src/tsconfig.json— use it if there is no root tsconfig- Otherwise, ask the user which one to analyze
- Root
- If none are found, tell the user this skill requires a TypeScript project with a
tsconfig.json
What ships with it
7 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.
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.
- 2mo ago First seen · 304 lines · 62 tokens per session scan C 8ffd56ed7cba
tsc-trace-analyzer is a skill published in the GitHub repository itaisatati/tsc-trace-analyzer (5 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 3,690 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tsc-trace-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tsc-trace-analyzeritaisatati/tsc-trace-analyzer | Skill | 5 | 7mo ago | MIT | C | 62 | Claude Code, Codex |
| cli-wiringgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 0 | Claude Code, Codex |
| agents-sdk-typescript-debuggingmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 125 | Claude Code |
| configkubb-labs/kubb | Skill | 1.8k | yesterday | MIT | A | 49 | Claude Code |
| angularericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 89 | Claude Code, Codex |
| node-modules-inspectorantfu/node-modules-inspector | Skill | 3.0k | 1mo ago | MIT | A | 156 | Claude Code, Codex |
| extending-personhog-test-harnessPostHog/posthog | Skill | 41k | yesterday | none | A | 134 | Claude Code, Codex |