Borrowing it
Nothing to install: this file belongs to himanshusaini-afk/buggy. 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/himanshusaini-afk/buggy/main/.kiro/steering/buggy-type-narrowing.mdgit clone --depth 1 https://github.com/himanshusaini-afk/buggyWrote 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/instructions/himanshusaini-afk/buggy/buggy-type-narrowing)<a href="https://agentmods.dev/instructions/himanshusaini-afk/buggy/buggy-type-narrowing"><img src="https://agentmods.dev/badge/instructions/himanshusaini-afk/buggy/buggy-type-narrowing/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/instructions/himanshusaini-afk/buggy/buggy-type-narrowing"><img src="https://agentmods.dev/badge/instructions/himanshusaini-afk/buggy/buggy-type-narrowing.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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
buggy buggy-type-narrowing.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buggy — Type Narrowing Suggestions
When Buggy proves a bug exists, suggest TypeScript type-level fixes that would prevent the bug at compile time — moving the check from runtime to the type system.
Triggering Phrases
- "how can I prevent this at the type level?"
- "make this type-safe"
- "prevent this class of bug"
- "strengthen the types"
Workflow
After a Bug is Proven
When buggy_investigate returns a proof certificate, analyze the root cause and suggest type-level prevention:
Pattern: Unbounded Numeric Input
Bug: discountPercent > 100 causes negative result
Type fix: Branded type
type Percent = number & { readonly __brand: unique symbol };
function asPercent(value: number): Percent {
if (value < 0 || value > 100) throw new RangeError(`${value} is not a valid percent`);
return value as Percent;
}
function applyDiscount(price: number, discount: Percent): number {
return price - (price * discount / 100); // Now safe — discount is always 0-100
}
Pattern: Division by Zero (Empty Array)
Bug: items.length === 0 causes NaN
Type fix: NonEmpty array type
type NonEmptyArray<T> = [T, ...T[]];
function calculateAverage(items: NonEmptyArray<CartItem>): number {
const total = items.reduce((sum, item) => sum + item.price, 0);
return total / items.length; // Safe — items.length >= 1
}
Pattern: Nullable Return Without Check
Bug: result is null but caller doesn't check
Type fix: Explicit Result type
type Result<T, E = Error> = { ok: true; value: T } | { ok: false; error: E };
function findUser(id: string): Result<User, 'not_found' | 'invalid_id'> {
// Caller MUST handle the error case — TypeScript enforces it
}
Pattern: Non-Deterministic Behavior
Bug: Function uses Math.random() making it non-deterministic
Type fix: Explicit effect type or dependency injection
interface RandomSource {
next(): number; // 0-1
}
// Now the randomness is injectable and testable
function calculateLoyaltyPoints(total: number, random: RandomSource): number {
const bonus = random.next() > 0.5 ? 10 : 0;
return Math.floor(total / 10) + bonus;
}
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.
- 4d ago First seen · 125 lines · 806 tokens per session scan A 139980ab3a0b
buggy buggy-type-narrowing.md is an instructions file published in the GitHub repository himanshusaini-afk/buggy (0 stars, last pushed 3d ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-09-08.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).