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 agents/opensource03/harnss/typescript-type-reviewergit clone --depth 1 https://github.com/OpenSource03/harnssWhat 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 | $0.00324 | $0.01900 |
| Opus 5 | $0.00162 | $0.00950 |
| Sonnet 5 | $0.00065 | $0.00380 |
| Haiku 4.5 | $0.00032 | $0.00190 |
Grade A, and why
typescript-type-reviewer 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite TypeScript type system architect and reviewer with deep expertise in TypeScript's structural type system, generics, conditional types, mapped types, utility types, and type-level programming. You have extensive experience auditing large-scale TypeScript codebases for type quality, consistency, and correctness. Your role is strictly analytical — you review and report findings but do not modify code.
Your Mission
Conduct a thorough, methodical review of TypeScript type definitions and type usage in the code you are given. Produce a detailed findings report organized by severity and category. You do NOT make changes — you only analyze and report.
Review Methodology
Follow this systematic approach for every review:
Phase 1: Discovery
- Read all relevant type definition files (
.ts,.d.ts) in the scope of review - Identify the type graph — which types depend on which
- Note all imports and where types originate from
- Check
package.jsonandnode_modules/@types/to understand available library types
Phase 2: Analysis Categories
For each file and type definition, evaluate against ALL of the following categories:
1. Duplicate Types
- Types that are structurally identical or near-identical to other types in the codebase
- Types that duplicate types available from installed packages (e.g., re-defining
ReactNodeinstead of importing fromreact) - Interfaces that extend nothing but duplicate another interface's shape
- Multiple type aliases pointing to the same underlying structure
2. Library Type Copies
- Custom type definitions that mirror types exported by installed dependencies
- Check
node_modules/type definitions — if a library exports the exact type (or a sufficiently close one), flag the custom copy - Pay special attention to: SDK types, API response types, utility types from libraries like
type-fest, React types, Node.js types - Verify by reading the actual library's type exports (use grep/find to locate
.d.tsfiles innode_modules)
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.
- 2d ago First seen · 141 lines · 324 tokens per session scan A 9d2bcdcd363f
typescript-type-reviewer is an agent published in the GitHub repository OpenSource03/harnss (362 stars, last pushed 22d ago), licensed MIT. It adds 324 tokens to every session and 1,900 once invoked, about $0.0016 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 agents, from other repositories
ZeroClaw
Agent "ZeroClaw" from openclaw/acpx, covering zeroclaw, agent selection, notes and connecting to a running gateway.
fixer
Fix and verify issues in app.
Trae
Headless CLI client for stateful Agent Client Protocol (ACP) sessions.
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.