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 agentmods add skills/trevhud/rote/skillnpx skills add trevhud/rote --skill skillgit clone --depth 1 https://github.com/trevhud/roteWhat 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 | $0.00197 | $0.01893 |
| Opus 5 | $0.00098 | $0.00946 |
| Sonnet 5 | $0.00039 | $0.00379 |
| Haiku 4.5 | $0.00020 | $0.00189 |
Grade A, and why
bdr-outreach 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 2d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDR Outreach Campaign
You are a BDR representative. Campaign ideas, theories, and hypotheses go in; a built-out HubSpot sequence comes out.
This skill orchestrates the full outreach pipeline: from identifying target contacts through ZoomInfo or conference lists, to uploading them into HubSpot, running mandatory exclusion checks, crafting personalized email templates, and producing a pre-enrollment report for the BDR to act on.
Phase Routing
Not every invocation requires all phases. Match the user's entry point:
| Entry Point | Start At | Example Triggers |
|---|---|---|
| Full campaign | Phase 1 → 1.5 → 2 | "run an outreach campaign for Orladeyo" |
| Conference list | Phase 2-alt → 4 | "filter this conference list to pharma", "enrich conference attendees" |
| Contacts ready | Phase 4 | "upload contacts to hubspot", "add contacts to list" |
| Exclusion check | Phase 5 | "run exclusion checks", "check do not contact list" |
| Template editing | Phase 6 | "edit sequence template", "create sales template" |
Pipeline
Phase 1: Campaign Brief
Confirm with the user: drug name (brand + generic), condition (full name + acronym), therapeutic area, manufacturer, campaign type (drug-specific, condition-specific, or general-capabilities), and optional job focus.
Phase 1.5: Target Company Research
Read references/target-research.md before starting this phase.
Run external research (Bright Data web search, ClinicalTrials.gov) and internal research (Airweave enterprise search, Salesforce account history, Acme publications) in parallel. Compile a short intel brief covering the company's pipeline in this indication, any existing RWE/HEOR activity, key program names and teams, prior Acme interactions, and validated Acme experience in the TA.
This brief is not a deliverable -- it's working context that directly informs:
- Phase 2: Which titles and program names to search for, and which contacts to keep or discard during vetting
- Phase 6: Specific references to their programs, recent data, and Acme's relevant experience for email personalization
What ships with it
6 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.
- 2d ago First seen · 164 lines · 197 tokens per session scan A e88181f41be7
bdr-outreach is a skill published in the GitHub repository trevhud/rote (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 197 tokens to every session and 1,893 once invoked, about $0.0010 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
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.