Borrowing it
Nothing to install: this file belongs to calven-ai/demoverse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/calven-ai/demoverse/main/.claude/skills/pipeline-update/SKILL.mdgit clone --depth 1 https://github.com/calven-ai/demoverseWrote 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/calven-ai/demoverse/pipeline-update)<a href="https://agentmods.dev/skills/calven-ai/demoverse/pipeline-update"><img src="https://agentmods.dev/badge/skills/calven-ai/demoverse/pipeline-update/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/calven-ai/demoverse/pipeline-update"><img src="https://agentmods.dev/badge/skills/calven-ai/demoverse/pipeline-update.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 | $0.00080 | $0.01461 |
| Opus 5 | $0.00040 | $0.00731 |
| Sonnet 5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
pipeline-update 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pipeline-update
The heartbeat of the demo world. One increment = one week of a real B2B SaaS pipeline: a couple of deals open, the open ones each take one step forward, the ones that have run their cycle close, and every one of those events leaves the one or two touch points a real team would have left behind.
This is not /backfill-opps. That one takes a deal that already exists and
generates its entire sales cycle at once. That is the historical seed motion.
This one adds a thin slice of new life to many deals. Never generate a full
detail layer for a deal here. A deal born this week has had exactly one
discovery call, and maybe an intro email. Its Evaluation call has not happened
yet. It happens in a later increment, when the deal reaches Evaluation.
Steps
-
Advance.
npm run pipeline(one week). For a longer jump or a heavier intake:npm run apply -- --weeks=N --new-opps=M.The engine echoes the active Tier-2 directives, the resolved increment, and any
--new-oppsoverride before writing anything. Read that back and confirm it is what was asked for. It then prints touch points planted this increment, grouped by deal:opp-291 Acme Corp (Discovery/open) art-xxx:call_transcript art-xxy:email_exchange opp-285 Veltrix (Negotiation/open) art-xxz:call_transcript opp-278 Orchard Ledger (Closed/lost) art-xya:survey art-xyb:ae_noteThat grouping is the work list. A forced increment steps
simNowpast the real calendar. The engine warns how far ahead the world will sit. If it is already several periods ahead, say so and let the operator decide before continuing. -
Fill: one
opp-fillersubagent per deal, in parallel. An increment is small (a handful of artifacts spread over several deals), so launch the whole wave at once: one subagent peropp-line above, plus one for any unattached artifacts (competitive_q). Give each the request dir (state/requests/<periodIndex>/) and only its artifact ids.
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.
- 12d ago First seen · 105 lines · 80 tokens per session scan A 3fccbc93e711
pipeline-update is a skill published in the GitHub repository calven-ai/demoverse (4 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,461 once invoked, about $0.0004 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
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
crm-customer-management
Orchestrate CRM workflows across Salesforce, HubSpot, Zoho, and Pipedrive — customer 360 lookups, deal pipeline management, activity logging, and customer onboarding. Use when looking up a customer, checking deal status, logging a call or meeting, reviewing pipeline health, onboarding a new customer, finding stalled…
Attio Automation
Automate Attio CRM operations -- search records, query contacts and companies with advanced filters, manage notes, list attributes, and navigate your relationship data -- using natural language through the Composio MCP integration.
Capsule CRM Automation
Automate Capsule CRM operations -- manage contacts (parties), run structured filter queries, track tasks and projects, log entries, and handle organizations -- using natural language through the Composio MCP integration.
b2b-sdr-agent
Autonomous AI Sales Development Rep for B2B export — handles lead discovery, BANT qualification, multi-channel outreach (WhatsApp/Email/Telegram), CRM management, and deal pipeline tracking. Built for cross-border trade.
Attio Automation
Automate Attio CRM operations -- search records, query contacts and companies with advanced filters, manage notes, list attributes, and navigate your relationship data -- using natural language through the Composio MCP integration.