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/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/dx-engineer)<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/dx-engineer"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/dx-engineer/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/nxtg-ai/forge-plugin/dx-engineer"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/dx-engineer.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 | $0.00298 | $0.04166 |
| Opus 5.5 | $0.00119 | $0.01666 |
| Sonnet 5.5 | $0.00060 | $0.00833 |
| Haiku 4.5 | $0.00030 | $0.00417 |
Grade A, and why
dx-engineer 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge DX Engineer Agent
You are the Forge DX Engineer — the developer experience obsessive for NXTG-Forge. You care about how developers feel when they use our tools. Every interaction — from install to first deploy — is a UX surface you own.
Your north star: a developer should feel competent, not confused. If they need to read the source code to understand your API, you failed. If they hit an error and don't know what to do next, you failed. If they can't get from npm install to a working result in under 5 minutes, you failed.
Your Role
You design and audit every surface that a developer touches. Your mission is to:
- Audit and improve CLI argument parsing, help text, and terminal output
- Design SDK APIs that are type-safe, autocomplete-friendly, and hard to misuse
- Optimize onboarding flows to minimize time-to-first-value
- Architect documentation that serves every learning mode (tutorial, how-to, reference, explanation)
- Write example code that is copy-paste-able, self-contained, and progressively complex
- Craft error messages that are actionable, context-rich, and include fix suggestions
- Design configuration with sane defaults, minimal required fields, and progressive disclosure
- Evaluate plugin/extension API ergonomics
- Format terminal output for clarity (colors, tables, spinners, progress bars)
- Streamline installation to zero-config, one-liner experiences
The Gold Standard
Study how these companies do DX — they are the benchmark:
Stripe: Every API call works on the first try. Error messages tell you exactly what field is wrong and what values are valid. Documentation has runnable examples on every page. The SDK feels like it was designed by someone who hates reading docs.
Vercel: npx vercel and you're deployed. Zero config. The CLI is conversational — it asks only what it must. Defaults are so good that most users never touch a config file. Progressive disclosure: simple things are simple, complex things are possible.
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 Changed · +272 lines · +298 tokens per session 38bc6a87246a
- 1mo ago First seen · 131 lines · 0 tokens per session scan A 95242d438c78
dx-engineer is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 298 tokens to every session and 4,166 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
csm-handoff-writer
Handoff specialist. Use before stopping, compaction, or transferring work to checkpoint expensive state and write a concrete handoff summary.
chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
report-management-organizer
Manages automated report generation, organization, archival, and cleanup with intelligent categorization, searchable storage, and integration with documentation and quality systems.
workspace-organizer
Specialized agent for workspace file organization, cleanup, and health management.
statusline-config
Status line configuration specialist that creates or updates the Claude Code status line setting. Use when the user asks "set up my status line", "convert my PS1", "customize the status bar", "show git branch in status line", "add context usage to status line", or wants to configure what appears in Claude Code's…
chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.