What is pipeline-followup?

A draft-only assistant for preparing follow-up emails for CRM deals that have stopped receiving replies. A CRM is a system for tracking sales opportunities and customer interactions.

Use it to find suitable no-reply deals, draft follow-up messages from Gmail and CRM context, and flag deals that have reached the allowed follow-up limit.

It helps identify stalled deals and prepare replies while keeping sending and CRM changes under the person's control.

pipeline-followup — Skill for Claude Code by yempik-ai

Install

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.

Any agent

npx skills add yempik-ai/cowork-os --skill pipeline-followup

Clone the repo

git clone --depth 1 https://github.com/yempik-ai/cowork-os

Made for: Claude Code.

Or install cowork-os, the plugin that ships this one along with the rest of its 4 skills, 7 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yempik-ai/cowork-os/pipeline-followup/github.svg)](https://agentmods.dev/skills/yempik-ai/cowork-os/pipeline-followup)

Your own site

<a href="https://agentmods.dev/skills/yempik-ai/cowork-os/pipeline-followup"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/pipeline-followup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yempik-ai/cowork-os/pipeline-followup"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/pipeline-followup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 980 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00156	$0.00980
Opus 5	$0.00078	$0.00490
Sonnet 5	$0.00031	$0.00196
Haiku 4.5	$0.00016	$0.00098

Measured 12d ago against content hash a3afc40f1d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pipeline-followup 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.

plugins/cowork-os/skills/pipeline-followup/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline follow-up — bozze per i deal silenziosi

Prepari bozze di follow-up per i deal che si sono raffreddati. On-demand: la persona ti chiama quando vuole recuperare i thread fermi. Non sei una routine automatica e non invii mai nulla.

Non-negoziabili (paletti)

Draft-only. Crei una bozza in Gmail (mai invio). Il destinatario e l'oggetto sono pronti, ma l'invio lo fa la persona.
Non toccare il CRM. Non spostare stadi, non chiudere deal, non modificare campi. Al massimo, se rules.md lo consente, proponi di aggiungere una nota/attività — ma solo su conferma esplicita.
Rispetta le regole in pipeline/rules.md. Soglia no-reply e numero massimo di follow-up: se un deal ha già ricevuto il massimo, non generare un'altra bozza — segnalalo come "da marcare freddo".
Mai inventare. Nessun prezzo, promessa, data o fatto che non sia già nel thread Gmail o nelle note del CRM. Se manca il contesto, dillo e chiedi.
Conferma prima dei volumi. Se i deal candidati sono più di ~5, elencali prima e chiedi su quali preparare le bozze, invece di generarne venti.

Preflight

Leggi pipeline/rules.md. Se è un template vuoto ({{placeholder}}), fermati: serve prima la sessione knowledge-transfer sul processo di vendita. Non inventare soglie.
Leggi pipeline/followup_templates.md per la voce e i template per situazione.
Verifica i connettori: CRM (es. Pipedrive, lettura) e Gmail (lettura + creazione bozze). Se manca uno dei due, dillo e fermati sul pezzo che non puoi fare.

Flusso

Individua i candidati. Dal deal radar (pipeline/deal_radar.md) se è fresco, o interrogando il CRM: deal con silenzio oltre la soglia del loro tipo (vedi rules.md). Se la persona ha nominato un deal specifico ("il deal Rossi"), lavora solo su quello.
Per ogni deal candidato, leggi il thread Gmail reale. Trova l'ultimo scambio con il referente: cosa è stato mandato, cosa è rimasto in sospeso, il tono. La bozza si aggancia a QUESTO, non a un template generico.
Scegli il template giusto in base alla situazione (primo follow-up / secondo / deal fermo in negoziazione) e adattalo al thread: 3-6 righe, voce della persona, un solo next step chiaro.
Crea la bozza in Gmail (in risposta al thread, così mantiene oggetto e destinatario). Non inviare.
Riepiloga alla persona: per ogni deal, 1 riga — "{{deal}}: bozza pronta, angolo = {{...}}". Segnala i deal che hanno superato il max follow-up (→ "da marcare freddo, non ricontatto"). Elenca cosa NON hai potuto fare (contesto mancante, connettore assente).

Read the full file on GitHub · 31 lines

Changes

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 · 31 lines · 0 tokens per session scan A a3afc40f1d4f

Subscribe to this mod's changes

pipeline-followup is a skill published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 156 tokens to every session and 980 once invoked, about $0.0008 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 2026-08-30.

LLM Marketing and SEO ai-agents automation claude claude-cowork knowledge-management

bach

Zentrales Verwaltungssystem für BACH. Dies ist der EINZIGE Skill der bei Claude hochgeladen werden muss. Er kennt alle lokalen Skills, führt Versions-Checks durch und lädt bei Bedarf aktuellere lokale Versionen. Aktiviert sich automatisch bei jeder Skill-Nutzung.

ellmos-ai/bach · 57 tokens

test-agent

Systematisches Testen von BACH und anderen LLM-OS-Systemen. Orchestrator fuer Test- und Vergleichs-Workflows.

ellmos-ai/bach · 33 tokens

persoenlicher-assistent

Boss-Agent fuer Alltags- und Arbeitsorganisation. Nutze diesen Skill wenn: (1) Briefings oder Dossiers benoetigt werden, (2) Termine vorbereitet werden sollen, (3) Locations gesucht werden, (4) Kalender verwaltet werden soll, (5) Haushalt organisiert werden soll. Koordiniert Experten: Haushaltsmanagement.

ellmos-ai/bach · 76 tokens

pipeline-followup