fiber-ai-plugin: Agent for Claude Code

.opencode/agents/ai-recruiter.md

ai-recruiter is an agent for Claude Code, OpenCode from fiber-ai/fiber-ai-plugin. It costs 148 tokens per session (2,385 once invoked), scanned A, original, MIT.

A recruiting assistant focused on finding and enriching candidates with Fiber AI. Candidate enrichment means adding information such as professional profiles or other details to people discovered during a search.

In plain words
What is it for?
Use it to build candidate pipelines, find engineers or go-to-market staff, identify people open to roles, connect GitHub contributors with LinkedIn profiles, or run recruiting outreach.
Why use it?
It helps turn an unclear hiring request into a focused candidate search while keeping track of data-retrieval costs before paid lookups run.

Agent for Claude CodeOpenCode

Written for Claude Code and OpenCode: shipped in a Claude Code plugin, but also installed under .opencode/. Also seen: model in frontmatter; mentions subagents.

This is fiber-ai/fiber-ai-plugin's own configuration. It tells Claude Code and OpenCode how to work on fiber-ai-plugin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fiber-ai-plugin configures →

Part of the fiber plugin — 16 skills, 4 commands, 7 agents, 3 MCP servers shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/fiber-ai/fiber-ai-plugin/main/.opencode/agents/ai-recruiter.md
Clone the repo
git clone --depth 1 https://github.com/fiber-ai/fiber-ai-plugin

Made for: Claude Code, OpenCode.

Or install fiber, the plugin that ships this one along with the rest of its 16 skills, 4 commands, 7 agents, 3 MCP servers.

Wrote 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.

agentmods badge for ai-recruiter

README.md
[![agentmods](https://agentmods.dev/badge/agents/fiber-ai/fiber-ai-plugin/ai-recruiter.svg)](https://agentmods.dev/agents/fiber-ai/fiber-ai-plugin/ai-recruiter)
Your own site
<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>
Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash ed5c495e9c8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.opencode/agents/ai-recruiter.md · 115 lines

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)

  1. 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.
  2. Always surface credit cost before running any reveal that will charge. Use getOrgCredits and estimateEnrichmentCost up front. Never charge silently.
  3. 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
  4. Recruiting-grade contact data is not sales-grade. Default to syncQuickContactReveal for single reveals, which returns work AND personal email in one call. Fall back to syncTurboContactEnrichment only if the quick tier returns nothing on a profile you really need. For lists of 10-2000 use startBatchContactDetails + pollBatchContactDetails.
  5. 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-handles covers the GitHub -> LinkedIn crosswalk.
  6. 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 MCP list_all_endpoints tool. If you are unsure, use get_endpoint_details_full on the Core MCP before calling.

Read the full file on GitHub · 115 lines

Changes

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.

  1. 7d ago First seen · 115 lines · 148 tokens per session scan A ed5c495e9c8b

Subscribe to this mod's changes

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.