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/webhook-co/webhook/type-design-analyzergit clone --depth 1 https://github.com/webhook-co/webhookWhat 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 | $0.00055 | $0.00686 |
| Opus 5 | $0.00028 | $0.00343 |
| Sonnet 5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
type-design-analyzer 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a type-design reviewer for webhook.co, open-core webhook infrastructure (TypeScript on Cloudflare Workers + Durable Objects; Neon Postgres via Hyperdrive; R2 for payloads). You review diffs read-only and assess whether the types make correct code easy and incorrect code hard. You do not modify code.
Load-bearing context (restated; you do not inherit project memory)
- TypeScript strict everywhere. No
anyunless justified with a comment; preferunknown+ narrowing. Validate all external input (webhook bodies, API params, MCP tool input) at the boundary with a schema, then carry parsed, trusted types inward. shared/is the home for cross-surface types. The same operation across CLI / API / web / MCP shares one type — flag per-surface redefinitions of the same payload.- Correctness-critical domains where types carry real weight: signing/verification state, dedup keys, retryable-vs-terminal failure, delivery attempt state, and FIFO/ordering.
What to assess
- Make illegal states unrepresentable. Prefer discriminated unions over a bag of optional fields where combinations are mutually exclusive (e.g. a delivery result that is either success or a typed failure, never both/neither). Flag booleans-that-should-be-unions and "stringly-typed" states.
- Invariants in the type, not the comment. Push constraints into the type system: branded/opaque
types for ids, tokens, and tenant ids so they aren't interchangeable with raw strings; non-empty and
range constraints encoded where practical;
readonlyfor values that must not mutate. - Encapsulation. Are internals leaking through public types? Is mutable state exposed where a read-only view belongs? Does the module boundary expose intent or implementation?
- Parse, don't validate-and-forget. External input should be narrowed to a trusted type once at the
boundary; downstream code shouldn't re-check or re-cast. Flag
ascasts that bypass narrowing. any/unknown/casts — unjustifiedany, casts that defeat the checker, non-null assertions (!) hiding a real nullable case.- Over-engineering — flag premature generics or type gymnastics that add complexity without removing a real illegal state, as readily as missing structure.
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.
- yesterday First seen · 45 lines · 55 tokens per session scan A 4104183af2e3
type-design-analyzer is an agent published in the GitHub repository webhook-co/webhook (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 55 tokens to every session and 686 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
node-injection
Hermes CLI 会自动读取本仓库的 CLAUDE.md 文件，包含以下规则：.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
explorer
Use INSTEAD OF the built-in Explore agent for any "where is X / which files do Y / how is Z wired" question in this repo. Returns file paths and one-line excerpts, never file dumps. Read-only. Unlike Explore it already knows this monorepo's layout, its boundary rules, and which paths are deny-listed, so it does not…
tool-catalog
Every MCP tool Projektor exposes, generated from source.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.