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/carolinacherry/github-talent-mcpWrote 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/plugins/carolinacherry/github-talent-mcp/marketplace)<a href="https://agentmods.dev/plugins/carolinacherry/github-talent-mcp/marketplace"><img src="https://agentmods.dev/badge/plugins/carolinacherry/github-talent-mcp/marketplace/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/plugins/carolinacherry/github-talent-mcp/marketplace"><img src="https://agentmods.dev/badge/plugins/carolinacherry/github-talent-mcp/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
github-talent-marketplace 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.
What it actually says
{
"name": "github-talent-marketplace",
"owner": {
"name": "carolinacherry"
},
"metadata": {
"description": "GitHub developer search and ranking tools for technical recruiting"
},
"plugins": [
{
"name": "github-talent-mcp",
"description": "Search, score, and rank GitHub developers for technical recruiting. 9 tools: plan_search, search_developers, get_developer_profile, rank_candidates, score_against_jd, compare_candidates, bulk_score, generate_outreach, get_repo_contributors.",
"source": {
"source": "github",
"repo": "carolinacherry/github-talent-mcp"
},
"version": "0.5.0",
"homepage": "https://github.com/carolinacherry/github-talent-mcp",
"category": "developer-tools",
"keywords": ["recruiting", "github", "talent", "mcp", "sourcing", "hiring"]
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 24 lines scan A 558bd33e065f
github-talent-marketplace is a plugin published in the GitHub repository carolinacherry/github-talent-mcp (9 stars, last pushed 20d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
github-remote
Read-first wrapper around the GitHub REST API — one-call PR/branch overviews (state + checks + reviews + runs), name-resolved PRs and issues, --wait on async flows, --json on lists. Zero token leakage. One write: pr comment.
hcloud-remote
Minimal CLI for Hetzner Cloud day-to-day ops — list/show servers, reboot, snapshot, ssh. Resolves servers by name so you never copy IDs around, and prints IPv4/IPv6 cleanly without the Python heredoc dance that breaks on Windows.
hermes-remote
Remote CLI for managing a Hermes Agent deployment over REST — cron jobs, env, status, model. Works against any Hermes instance (Coolify, bare VPS, etc.).
langfuse-remote
Remote CLI for managing a Langfuse instance (cloud or self-hosted) — export/import prompts for backup and cross-env migration, smoke-test trace ingestion, health checks across multiple instances.
openrouter-remote
CLI for OpenRouter — check balance, list/filter/compare models by price and capabilities, manage API keys via the provisioning endpoint. Designed for both interactive use from Claude Code and for Hermes cron jobs (balance alerts, usage summaries).
railway-ops
Read-first wrapper around the Railway CLI — single-call env overviews (services, deploy status, recent errors/warnings, env var NAMES-only) for fast incident triage. Zero env-var-value leakage.