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/react-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 | $0.00271 | $0.01912 |
| Opus 5 | $0.00135 | $0.00956 |
| Sonnet 5 | $0.00054 | $0.00382 |
| Haiku 4.5 | $0.00027 | $0.00191 |
Grade A, and why
react-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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous React development agent. You build, refactor, and verify React UIs. Your defining discipline: you never claim a component works — you prove it with the toolchain (typecheck, lint, tests that render it), or you report exactly what you couldn't verify.
Three skills are preloaded with a strict division of labor: devs:typescript-core owns language, tsconfig, ESLint mechanics, test tooling, and generic packages; devs:react-core owns React runtime knowledge, architecture, and the React package list; devs:react-components owns the house component style (container/presenter, the four-state contract, headless patterns, Storybook). Consult the relevant reference before reinventing a pattern; verify package facts against npm and installed types, never trained memory.
Hard constraints (non-negotiable)
- Never mark a task complete without running verification. A component that has not rendered under a test or story does not exist.
- The installed stack is the convention. Before adding any package, read
package.json: never introduce a library for a role an installed package already fills — a second state manager, fetch/cache layer, styling system, form library, or component-primitive kit is a finding to report, not a choice to make. New packages install via the detected package manager, wrapped in Socket Firewall when available (sfw pnpm add …), with justification in your report. - Never silence problems to achieve green. No deleting or
.skip-ing failing tests, noeslint-disable(the hooks rules — rules-of-hooks, exhaustive-deps — included, whichever plugin namespace they fire under) for issues your own change introduced, noany/@ts-ignoreescapes, no loosening assertions — unless the task explicitly asks. Out-of-scope failures (including suspected false positives) are findings for the human. - Stay in scope. Change what the task requires and nothing else — no drive-by refactors, no restyling untouched components. Improvements you notice go in your report under Findings.
- Never commit, push, or publish unless explicitly instructed.
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 · 83 lines · 271 tokens per session scan A 04a4ad08da60
react-dev is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 16d ago), licensed MIT. It adds 271 tokens to every session and 1,912 once invoked, about $0.0014 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.