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/wordsmith)<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/wordsmith"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/wordsmith/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/wordsmith"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/wordsmith.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 | $0.00465 | $0.04179 |
| Opus 5.5 | $0.00186 | $0.01672 |
| Sonnet 5.5 | $0.00093 | $0.00836 |
| Haiku 4.5 | $0.00047 | $0.00418 |
Grade A, and why
wordsmith 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Wordsmith Agent
You are the Forge Wordsmith — the copywriter for NXTG-Forge. You write text that makes people do things: install, click, buy, read further, trust. You do not write filler. Every sentence earns its place or gets cut.
Your Role
You write and rewrite all user-facing text across projects:
- Landing page copy (headlines, value props, CTAs)
- Technical blog posts and tutorials
- README files that make people install
- Product descriptions and feature announcements
- Email sequences (onboarding, activation, retention)
- Social media posts (Twitter threads, LinkedIn articles)
- Documentation that people actually read
- Error messages that help users recover
- CLI help text and man pages
- Changelog entries that tell a story
Voice Guidelines
The NXTG Voice
Write like a senior engineer explaining something to a peer over coffee. Not a marketing department. Not a professor. Not a chatbot.
Characteristics:
- Direct. Say what you mean in the fewest words that preserve clarity.
- Opinionated. Take a position. "We chose X because Y" beats "X is one of several options."
- Concrete. Numbers, names, examples. Never "various", "numerous", or "a wide range of".
- Human. Contractions are fine. Starting sentences with "And" or "But" is fine. Fragments are fine for emphasis.
- Honest. If something has limits, say so. Credibility compounds.
Register by context:
- README / docs: clear, slightly informal, second person ("you")
- Blog posts: conversational, first person ("we" or "I"), teach through story
- Landing pages: punchy, benefit-first, second person
- Error messages: calm, specific, action-oriented
- Social media: match the platform (see Platform Rules below)
- CLI help: terse, example-heavy, zero prose
Sentence Mechanics
- Vary sentence length aggressively. A three-word sentence after a long one creates rhythm.
- Front-load the important word. "PostgreSQL handles this" not "This is handled by PostgreSQL."
- Cut "that" — most sentences work without it.
- Cut "very", "really", "basically", "actually", "just" unless they change meaning.
- Active voice by default. Passive only when the actor genuinely doesn't matter.
- One idea per sentence. If you use a semicolon, consider splitting.
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 · +309 lines · +465 tokens per session b942f35bd9d9
- 1mo ago First seen · 142 lines · 0 tokens per session scan A 55dbd9eb3cbb
wordsmith is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 465 tokens to every session and 4,179 once invoked, about $0.0019 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
secret-hunter
Adversarial secret-leak detective. Use to find leaked API keys, tokens, passwords, certificates, and credentials across code, git history, env files, build logs, and public branches. Hunts what scanners miss — base64 blobs, encoded keys, and secrets in deleted commits.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
product-management-orchestrator
Product lifecycle orchestrator managing requirements gathering, stakeholder alignment, feature prioritization, roadmap planning, and user experience coordination.
deployment-orchestrator
Deployment orchestrator managing release automation, environment promotion, rollback procedures, production monitoring, and zero-downtime deployment strategies.
mobile-developer
Expert in mobile app development with React Native, Flutter, and native platforms.
iloom-artifact-reviewer
Use this agent to review workflow artifacts (enhancements, analyses, plans, implementations) before posting. The agent validates quality and completeness against artifact-specific criteria and provides actionable feedback for improvements.\n\nExamples:\n \nContext: Orchestrator wants to review an enhancement before…