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 skills add Comradery64/open-greenhouse-mcp --skill greenhouse-candidate-screeninggit clone --depth 1 https://github.com/Comradery64/open-greenhouse-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/skills/comradery64/open-greenhouse-mcp/greenhouse-candidate-screening)<a href="https://agentmods.dev/skills/comradery64/open-greenhouse-mcp/greenhouse-candidate-screening"><img src="https://agentmods.dev/badge/skills/comradery64/open-greenhouse-mcp/greenhouse-candidate-screening/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/skills/comradery64/open-greenhouse-mcp/greenhouse-candidate-screening"><img src="https://agentmods.dev/badge/skills/comradery64/open-greenhouse-mcp/greenhouse-candidate-screening.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00140 | $0.00902 |
| Opus 5 | $0.00070 | $0.00451 |
| Sonnet 5 | $0.00028 | $0.00180 |
| Haiku 4.5 | $0.00014 | $0.00090 |
Grade A, and why
greenhouse-candidate-screening 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 11d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Greenhouse candidate screening
Turns raw Greenhouse data about one candidate into a decision-ready summary, and safely handles any follow-up action the recruiter wants to take on that candidate.
When this applies
Trigger when the user names a specific candidate (by name, application ID, or a link) and wants an assessment, summary, or help deciding what to do with them. If the user instead wants a sweep across many candidates or a whole pipeline, use greenhouse-pipeline-search or greenhouse-resume-batch-review instead — this skill is for one candidate at a time.
How to do it
- Identify the candidate. If the user gave a name but there are multiple matches (common candidate names, or the same person applying to multiple jobs), ask which one before proceeding rather than guessing.
- Call
screen_candidatefor that candidate — it's the composite tool built for exactly this, pulling resume, application, and pipeline stage together in one call rather than making you stitch together several raw API calls. - Read the resume and application content it returns, not just the metadata. The recruiter wants your read on fit, not a reformatted copy of their resume.
- Note anything that would change how a recruiter should act on this: gaps in employment, mismatch between resume and job requirements, how long they've been sitting in the current stage, internal notes or scorecards already on file if the tool surfaces them.
- Give a plain-language recommendation — advance, hold, or pass — with the reasoning, not just a verdict. The recruiter is accountable for the hiring decision; your job is to make that decision easy to reach quickly, not to make it for them silently.
Output format
## Screening summary — [Candidate name]
**Job:** [job title] · **Stage:** [current pipeline stage] · **Applied:** [date/how long ago]
**Background:** [2-4 sentence synthesis of resume + application, focused on relevance to the role]
**Notable:** [anything that stands out — strong match, gap, overqualified, unclear fit, red flag worth double-checking — omit if nothing stands out]
**Recommendation:** [Advance / Hold / Pass] — [one or two sentence reasoning]
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.
- 11d ago First seen · 42 lines · 140 tokens per session scan A 3e08ddced1fe
greenhouse-candidate-screening is a skill published in the GitHub repository Comradery64/open-greenhouse-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 140 tokens to every session and 902 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…