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 pharmabridge-supply-findergit 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/pharmabridge-supply-finder)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/pharmabridge-supply-finder"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/pharmabridge-supply-finder/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/pharmabridge-supply-finder"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/pharmabridge-supply-finder.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 | $0.00068 | $0.00997 |
| Opus 5.5 | $0.00027 | $0.00399 |
| Sonnet 5.5 | $0.00014 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
pharmabridge-supply-finder 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PharmaBridge supply finder
Use this skill when someone needs a scarce medication or specific blood units and the only way to find them is to phone pharmacies or blood banks one by one. It drives a running PharmaBridge server, so every call goes through the same briefs, strict result schemas, and safety gate as the PharmaBridge app.
Requirements
- A running PharmaBridge server (
npm run devinapps/typescript/pharmabridge, defaulthttp://localhost:3000). SetPHARMABRIDGE_URLif it runs elsewhere. - Node.js 20 or newer. The helper has no dependencies.
- The helper sends operator codes and call tokens only to a loopback server (
http://localhost:3000by default) or to an https origin listed inPHARMABRIDGE_APPROVED_ORIGINS, never follows redirects, and masks phone numbers in everything it prints or saves. - Simulation needs nothing else. Live calls need the server's live gate (CALL-E key,
PHARMABRIDGE_LIVE_CALLS=true, an operator code, and a signing secret) plus the user's explicit approval for each dispatch.
Workflow
Run the helper from this skill folder: node scripts/pharmabridge.mjs <command> [options].
- Clarify the need. For medicine: drug, strength, form, and quantity. For blood: group, component, units, and the hospital where the patient is admitted. Also ask where to search.
- Resolve the medication (pharmacy searches only):
node scripts/pharmabridge.mjs drug --query "lisdexamfetamine 30 mg capsule"and pick the RxCUI. - Discover facilities. This never dials:
node scripts/pharmabridge.mjs discover --kind blood_bank --near "Chennai, India" --radius 8The list is saved topharmabridge-facilities.jsonwith masked numbers and discovery signatures. - Check the Shortage Pulse. Fresh answers from earlier PharmaBridge calls, shared without names:
node scripts/pharmabridge.mjs pulse --kind blood_bank --group O- --component plateletsSkip facilities that recently said they are out or won't say by phone, and tell the user when a recent answer already covers the need. Controlled medications are never named as in stock. - Preview the brief. This is a dry run that never dials:
node scripts/pharmabridge.mjs plan --kind blood_bank --group O- --component platelets --units 2 --hospital "General Hospital" --facility 1Show the user what the agent will say and which fields it will return. - Confirm with the user before any call: the facilities, the routing, and how many calls
will be used. Default to
--routing simulation. - Dispatch. Pass the same need options again:
node scripts/pharmabridge.mjs call --kind blood_bank --group O- --component platelets --units 2 --hospital "General Hospital" --facility 1,2,3 --routing simulationFor live calls, add--routing test_lineor--routing direct, plus--operator-code <code from the user>. Direct routing also needs--consent, and only after the user explicitly approves calling those businesses. - Collect results:
node scripts/pharmabridge.mjs wait. This polls until every call ends and savespharmabridge-results.json. - Report honestly. Lead with confirmed availability and quote the staff member's words. Keep refusals, voicemail, and unanswered calls in the report, and never turn "we can't say by phone" into "no". Offer the next step: hold or reserve through the PharmaBridge app, or share the result.
What ships with it
3 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 · 65 lines · 68 tokens per session scan A 1d4cde8001ed
pharmabridge-supply-finder is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 997 once invoked, about $0.0003 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 2026-09-16.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…