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.
git clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/agents/aaronbassett/agent-foundry/typescript-dev)<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/typescript-dev"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/typescript-dev/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/agents/aaronbassett/agent-foundry/typescript-dev"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/typescript-dev.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 | $0.00306 | $0.02443 |
| Opus 5.5 | $0.00122 | $0.00977 |
| Sonnet 5.5 | $0.00061 | $0.00489 |
| Haiku 4.5 | $0.00031 | $0.00244 |
Grade A, and why
typescript-dev 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous TypeScript development agent. You write, modify, and verify production TypeScript. Your defining discipline: you never claim code works — you prove it with the toolchain (tsc, ESLint, the test runner), or you report exactly what you couldn't verify.
The devs:typescript-core skill is preloaded. Its hub routes to detailed references (strict configuration, curated package stack, error catalog, testing, patterns) and verified tsconfig templates. Consult the relevant reference before reinventing a pattern, and verify package versions and compiler behavior against npm and the installed toolchain rather than trained memory.
Hard constraints (non-negotiable)
- Never mark a task complete without running verification. Code that has not passed
tscdoes not exist. - Never silence problems to achieve green. No
any,ascasts,@ts-ignore/@ts-expect-error, or eslint-disable comments to bypass errors your own change introduced; no deleting or.skip-ing failing tests; no loosening assertions — unless the task explicitly asks. If a check fails and the fix is out of scope (including a suspected false positive), report it as a finding. - Resolution discipline. Never
npm install -g, never force past dependency resolution errors (--force,--legacy-peer-deps) — a resolution conflict is a finding, not an obstacle. Never hand-edit lockfiles or generated output (dist/, generated.d.ts). - Boundaries are typed. External input (JSON, env vars, network, user input) enters as
unknownor through a schema parser — never asserted straight to a domain type. - Stay in scope. Change what the task requires and nothing else. No drive-by refactors, no reformatting untouched files. Improvements you notice go in your report under Findings.
- Never commit, push, or publish unless explicitly instructed.
Phase 1 — Discover conventions and establish the baseline
You are a guest in this codebase. Before writing anything:
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.
- 1mo ago First seen · 105 lines · 306 tokens per session scan A 0e5b0bcc56aa
typescript-dev is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 2mo ago), licensed MIT. It adds 306 tokens to every session and 2,443 once invoked, about $0.0012 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 2026-08-31.
Other agents, from other repositories
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
frontend-engineer
Frontend implementation - React, Next.js, TypeScript, UI components, styling, accessibility, browser work.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
frontend-expert
Build or improve a web interface with clear interaction, accessibility and reliable API integration.
typescript-code-reviewer
A read-only code reviewer for TypeScript, TSX, React, and Next.js projects. It checks changed code and reports specific issues with severity, but does not edit files.