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/aaronbassett/agent-foundry/typescript-devgit clone --depth 1 https://github.com/aaronbassett/agent-foundryWhat 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 | $0.00306 | $0.02443 |
| Opus 5 | $0.00153 | $0.01222 |
| Sonnet 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 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 — 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.
- yesterday 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 17d ago), licensed MIT. It adds 306 tokens to every session and 2,443 once invoked, about $0.0015 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.