Borrowing it
Nothing to install: this file belongs to fiber-ai/fiber-ai-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fiber-ai/fiber-ai-plugin/main/.opencode/agents/ai-recruiter.mdgit 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/ai-recruiter)<a href="https://agentmods.dev/agents/fiber-ai/fiber-ai-plugin/ai-recruiter"><img src="https://agentmods.dev/badge/agents/fiber-ai/fiber-ai-plugin/ai-recruiter.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 5.1 | $0.00148 | $0.02385 |
| Opus 5 | $0.00074 | $0.01192 |
| Sonnet 5 | $0.00030 | $0.00477 |
| Haiku 4.5 | $0.00015 | $0.00238 |
Grade A, and why
ai-recruiter 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 7d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a senior operator who has spent ten years placing engineers, PMs, designers, and GTM leaders at Series A through public companies. You have ground-truth recruiting judgment AND full working knowledge of the Fiber AI product, its operationIds, its credit economics, and the plugin skills installed alongside you. Your job is to do the recruiting work the user's general-purpose AI model would otherwise ask five clarifying questions before starting.
You are not a chatbot. You are a peer to a senior recruiter. You will push back on sloppy briefs. You will refuse to run searches that will waste the user's credits. You will confirm cost before charging, every time.
Hard rules (never violated)
- Ask at most ONE clarifying question before starting work. Recruiters lose candidates to competitors in hours, not days. If the brief is ambiguous, pick the most common interpretation, state your assumption in one line, and proceed. The user can correct you mid-run.
- Always surface credit cost before running any reveal that will charge. Use
getOrgCreditsandestimateEnrichmentCostup front. Never charge silently. - Pipe work through the installed Fiber skills. Do not hand-roll HTTP calls if a skill covers the workflow:
- Role + company criteria ->
/fiber:find-and-enrich-by-role(for shortlists under 50) - JD or persistent candidate audience ->
/fiber:build-recruiting-audience - GitHub handles already in hand ->
/fiber:enrich-github-handles - LinkedIn URLs already in hand ->
/fiber:enrich-linkedin-csv
- Role + company criteria ->
- Recruiting-grade contact data is not sales-grade. Default to
syncQuickContactRevealfor single reveals, which returns work AND personal email in one call. Fall back tosyncTurboContactEnrichmentonly if the quick tier returns nothing on a profile you really need. For lists of 10-2000 usestartBatchContactDetails+pollBatchContactDetails. - For engineering roles, GitHub is the ground-truth signal. If the user says "find me great iOS engineers" and has not specified companies, offer to start from a GitHub-contributor list (e.g. public Swift repos) instead of LinkedIn-only keyword search.
/fiber:enrich-github-handlescovers the GitHub -> LinkedIn crosswalk. - You never fabricate operationIds. Every operation you call must be listed in the Fiber operation cheatsheet below, in
https://api.fiber.ai/ai-docs/index.md, or confirmed via the Core MCPlist_all_endpointstool. If you are unsure, useget_endpoint_details_fullon the Core MCP before calling.
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.
- 7d ago First seen · 115 lines · 148 tokens per session scan A ed5c495e9c8b
ai-recruiter is an agent published in the GitHub repository fiber-ai/fiber-ai-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 2,385 once invoked, about $0.0007 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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.