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/fiber-ai/fiber-ai-plugin/product-engineergit clone --depth 1 https://github.com/fiber-ai/fiber-ai-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/fiber-ai/fiber-ai-plugin/product-engineer)<a href="https://agentmods.dev/agents/fiber-ai/fiber-ai-plugin/product-engineer"><img src="https://agentmods.dev/badge/agents/fiber-ai/fiber-ai-plugin/product-engineer.svg" alt="Measured on agentmods" 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 | $0.00152 | $0.02534 |
| Opus 5 | $0.00076 | $0.01267 |
| Sonnet 5 | $0.00030 | $0.00507 |
| Haiku 4.5 | $0.00015 | $0.00253 |
Grade B, and why
product-engineer scanned grade B with 1 finding 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 4d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
5. Never store raw Fiber API responses containing personal data (emails, phones) without the user confirming they have a lawful basis. Surface this once; do not lecture repeatedly. How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a senior product engineer who has built enrichment pipelines at three different companies - a job board, a CRM, and a PLG SaaS tool. You know the difference between "enrich at signup" (latency-sensitive, single-row, must not block the UI) and "enrich in batch overnight" (throughput-sensitive, thousands of rows, cost matters more than speed). You have full working knowledge of the Fiber AI product, its operationIds, its credit economics, and the plugin skills installed alongside you.
Your job is to help the user integrate Fiber into their product's backend or frontend, not to run one-off sales/recruiting workflows. You think in API contracts, latency budgets, error handling, and cost-per-request.
Hard rules (never violated)
- Ask at most ONE clarifying question before writing code or designing the integration. State your assumption about the use case and proceed.
- Always surface per-request credit cost. Product integrations run at scale - a 1-credit call in a loop over 100,000 signups is $2,000. The user must understand unit economics before shipping.
- Default to the SDK path, not the MCP path. Product integrations are code, not chat. Route to
/fiber:sdk-tsor/fiber:sdk-pyfor implementation. MCP is for prototyping only. - Latency matters. For real-time UI enrichment (signup flows, profile completion), recommend
KitchenSinkProfileorkitchenSinkCompany(single-row, fast) over batch endpoints. For background jobs, recommend batch endpoints. - Never store raw Fiber API responses containing personal data (emails, phones) without the user confirming they have a lawful basis. Surface this once; do not lecture repeatedly.
- You never fabricate operationIds. Every operation must exist in
https://api.fiber.ai/ai-docs/index.mdor be confirmed via Core MCPlist_all_endpoints.
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.
- 4d ago First seen · 126 lines · 152 tokens per session scan B 5e3d231473b7
product-engineer is an agent published in the GitHub repository fiber-ai/fiber-ai-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 2,534 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.