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 CALLE-AI/awesome-phone-call-agents --skill bounty-screening-callgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/bounty-screening-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/bounty-screening-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/bounty-screening-call/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/calle-ai/awesome-phone-call-agents/bounty-screening-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/bounty-screening-call.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 | $0.00052 | $0.01628 |
| Opus 5.5 | $0.00021 | $0.00651 |
| Sonnet 5.5 | $0.00010 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
bounty-screening-call 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bounty Screening Call
Use this skill when an agent has found a potentially legitimate technical bounty or contest and needs to verify unresolved public facts with the official organizer before doing claim or submission work. The skill is a fact-gathering step, not an application, claim, negotiation, payment, or payout-collection workflow.
The default path is a local preview. A compatible host may hand the frozen call
task to CALL-E only after the operator has explicitly authorized that one call,
confirmed the destination, and reviewed the preview. Read
references/safety.md before any live handoff and use
references/examples.md for the offline fixtures.
When To Use
- A public bounty listing has an official organizer contact but one or more of reward, AI-use, eligibility, deadline, payout, or submission facts are not independently confirmed.
- The operator wants a transcript-backed verification brief before deciding whether to invest engineering time or submit a claim.
- A host can preserve one stable request identifier and reconcile the terminal CALL-E result before any downstream action.
When Not To Use
- To call a guessed, scraped, private, or unrelated number.
- To ask for passwords, one-time codes, identity documents, bank/card details, payment credentials, PayPal links, or account access.
- To negotiate a reward, reserve a slot, submit a solution, accept legal terms, create an account, or promise delivery.
- To decide automatically that a bounty is safe, accepted, payable, or worth claiming. The result is advisory evidence for a human or a separate deterministic policy gate.
- For legal, tax, banking, or financial-advice questions. Ask only about the public payout route and record uncertainty.
Required Inputs
request_id: stable identifier for this one verification request.opportunity_id: stable listing or issue identifier.title: public bounty title.listing_url: HTTPS URL of the official listing or issue.organizer_name: public organizer or project name.organizer_phone_e164: one destination explicitly supplied or authorized by the operator; E.164 only.contact_basis: why the operator may contact this number (for example, an organizer-published support line plus the operator's current intent to call).reported_reward: amount and currency currently shown in public evidence.reported_ai_policy:allowed,limited,forbidden, orunknown.reported_eligibility:eligible,ineligible, orunknownfor the operator's jurisdiction.reported_deadline: ISO date/time orunknown.reported_payout_method:fiat,crypto,other, orunknown.public_evidence: short citations or quotes from the listing. Do not put secrets or private contact data here.operator_intent: an explicit statement that this single verification call is authorized now.
What ships with it
4 files beside SKILL.md 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 · 167 lines · 52 tokens per session scan A 7ac1cfaecfac
bounty-screening-call is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,628 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…