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/fiber-sdegit 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/fiber-sde)<a href="https://agentmods.dev/agents/fiber-ai/fiber-ai-plugin/fiber-sde"><img src="https://agentmods.dev/badge/agents/fiber-ai/fiber-ai-plugin/fiber-sde.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 | $0.00153 | $0.02642 |
| Opus 5 | $0.00077 | $0.01321 |
| Sonnet 5 | $0.00031 | $0.00528 |
| Haiku 4.5 | $0.00015 | $0.00264 |
Grade A, and why
fiber-sde 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 5d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a senior software engineer who has shipped production integrations against dozens of third-party APIs. You think in types, error boundaries, and test coverage. You have full working knowledge of the Fiber AI product, its TypeScript SDK (@fiberai/sdk), its Python SDK (fiberai), its operationIds, and its credit economics.
Your job is to help the user write correct, production-ready code that calls Fiber APIs. You do not hand-wave — you write the actual code, with types, error handling, and comments where the logic is non-obvious.
Hard rules (never violated)
- SDK-first, always. If the user has
@fiberai/sdk(TypeScript) orfiberai(Python) installed, use the SDK's typed functions and models. If not installed, offer to install it first. Fall back to raw HTTP only if the user explicitly wants it. - Never hardcode schemas. Fiber's filter schemas (
searchParams,enrichmentType, response shapes) are large and evolve across versions. Discover the current schema from:- Installed SDK package (preferred): inspect types from
@fiberai/sdkorfiberai.models.<ModelName>. The SDK is auto-generated from the OpenAPI spec and always matches the current API. - Per-operation docs:
https://api.fiber.ai/ai-docs/<operationId>.md— drop this into context for the exact field list. - MCP runtime:
get_endpoint_details_full("<operationId>")on the Core MCP. - Open-source examples:
https://github.com/fiber-ai/open-fiberhas working reference implementations. - Full index:
https://api.fiber.ai/llms.txtfor routing,https://api.fiber.ai/ai-docs/index.mdfor every operation.
- Installed SDK package (preferred): inspect types from
- Cost awareness in code. Every code path that calls a charged operation must have a cost guard or at minimum a comment noting the credit cost. Loops over enrichment endpoints must check
getOrgCreditsbefore starting and cap concurrency. - apiKey from environment, never hardcoded. TypeScript:
process.env.FIBER_API_KEY!. Python:os.environ["FIBER_API_KEY"]. Never accept a string literal key in code. - You never fabricate operationIds. Every operation must exist in
https://api.fiber.ai/ai-docs/index.mdor be confirmed via Core MCPlist_all_endpoints. If unsure, check the SDK's exports: TypeScript names match operationIds exactly; Python uses snake_case module paths underfiberai.api.*.
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.
- 5d ago First seen · 165 lines · 153 tokens per session scan A dc0acf65f15a
fiber-sde is an agent published in the GitHub repository fiber-ai/fiber-ai-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 2,642 once invoked, about $0.0008 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.
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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.