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 quivly/skills --skill renewal-forecastgit clone --depth 1 https://github.com/quivly/skillsWrote 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/quivly/skills/renewal-forecast)<a href="https://agentmods.dev/skills/quivly/skills/renewal-forecast"><img src="https://agentmods.dev/badge/skills/quivly/skills/renewal-forecast/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/quivly/skills/renewal-forecast"><img src="https://agentmods.dev/badge/skills/quivly/skills/renewal-forecast.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 | $0.00057 | $0.00609 |
| Opus 5 | $0.00028 | $0.00304 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
renewal-forecast 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 10d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renewal Forecast
You forecast renewals the way a disciplined sales leader forecasts pipeline: every deal categorized, every category defended with evidence.
Core principle: a forecast category without evidence is a guess — every account states the reasoning that earned its bucket.
Workflow
- Find all accounts with renewals in the target window (
search-customers,get-contracts) — default to the next quarter if unspecified. - For each renewal: contract value and terms (
get-contracts,get-billing-subscription), current health and trajectory (get-health-score), revenue history (get-revenue) for expansion/contraction precedent. - Assign each account a category, each with stated reasoning:
- Commit — healthy, engaged, no open risks
- Best case — likely but with an unresolved question (budget approval pending, champion new in seat)
- At risk — active risk factors; renewal requires intervention
- Likely churn — evidence points to non-renewal; plan for save attempt or graceful exit
- Note expansion potential inside the renewal (upsell at renewal is the cheapest expansion there is).
Output Format
Renewal forecast — {quarter}
Topline — total renewable ARR; commit / best case / at risk / likely churn split; weighted forecast
By account — table: account, ARR, date, category, one-line reasoning, next step
Swing accounts — the 2-3 accounts whose outcome most changes the quarter, and what would move them
Expansion inside renewals — where to attach upsell conversations
Guidelines
- Reasoning is mandatory — a category without evidence is a guess. "Commit because health 85, champion engaged, EBR done" is the standard.
- Confidence comes from engagement + value realization, not from the absence of complaints.
- Start-date awareness: an at-risk renewal 30 days out is a fire; the same at 150 days is a project.
Related skills: single-account depth → renewal-risk; accounts in the at-risk bucket → churn-save-plan.
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.
- 10d ago First seen · 49 lines · 57 tokens per session scan A e5e918417fc9
renewal-forecast is a skill published in the GitHub repository quivly/skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 609 once invoked, about $0.0003 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
nitrostack-tools-resources-prompts
Guidelines and patterns for defining Tools, Resources, and Prompts in a NitroStack application with schema validation via Zod, including caching, rate-limiting, and base64 file uploads.
prisma-postgres-setup
Set up a new Prisma Postgres database and connect it to a local project using the Management API. Use when asked to "set up a database", "create a Prisma Postgres project", "get a connection string", "connect my app to Prisma Postgres", or "provision a database".
nitrostack-middleware-pipeline
Best practices for implementing and applying Guards, Interceptors, Middleware, Pipes, and Exception Filters in the NitroStack SDK.
nitrostack-ui-widgets
Best practices for linking tools to interactive frontend widgets using @Widget and @nitrostack/widgets SDK (including state sync, tool calling, display modes, media queries, and chat actions).
prisma-cli
Prisma ORM CLI commands reference covering init, generate, migrate, db, dev, studio, validate, format, debug, and mcp. Use for ORM/database CLI workflows, not Prisma Compute app deployment. For Prisma Compute, @prisma/cli app deploy, compute:deploy, create-prisma --deploy, apps, deployments, logs, or domains, use the…
nitrostack-mcp-app-architecture
Best practices and guidelines for bootstrapping, defining modules, using dependency injection, managing server lifecycles, and handling events in the NitroStack SDK.