Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luanpdd/kit-mcpnpx agentmods add skills/luanpdd/kit-mcp/crm-lead-pipeline-patternsWrote 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/luanpdd/kit-mcp/crm-lead-pipeline-patterns)<a href="https://agentmods.dev/skills/luanpdd/kit-mcp/crm-lead-pipeline-patterns"><img src="https://agentmods.dev/badge/skills/luanpdd/kit-mcp/crm-lead-pipeline-patterns/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/luanpdd/kit-mcp/crm-lead-pipeline-patterns"><img src="https://agentmods.dev/badge/skills/luanpdd/kit-mcp/crm-lead-pipeline-patterns.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 | $0.00046 | $0.02965 |
| Opus 5.5 | $0.00018 | $0.01186 |
| Sonnet 5.5 | $0.00009 | $0.00593 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade A, and why
crm-lead-pipeline-patterns 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRM Lead Pipeline — Patterns Canônicos
Quando usar
LLM carrega esta skill ao implementar CRM lead pipeline em B2B multi-tenant. Trigger phrases:
- "CRM lead pipeline", "sales pipeline stages"
- "lead state machine Postgres", "transition validation"
- "ownership transfer lead", "lead assignment"
- "lead dedup phone email"
- "integração WhatsApp CRM lead"
Regras absolutas
REGRA #1 (6 stages canônicos): Pipeline tem 6 stages: lead → qualified → proposal → negotiation → won | lost. Custom stages permitidos via prefix custom_* mas estes 6 são obrigatórios.
REGRA #2 (trigger PG > CHECK constraint): Validar transições via trigger BEFORE UPDATE com RAISE EXCEPTION, não apenas CHECK constraint. CHECK valida valor, mas não valida transição (lead → won direto = bug, deve passar por qualified+proposal+negotiation).
REGRA #3 (ownership transfer com audit): Mudança em leads.owner_id SEMPRE dispara: (a) notificação ao novo owner, (b) entry em audit_logs com previous_owner_id, new_owner_id, reason. Trigger AFTER UPDATE.
REGRA #4 (dedup unique constraints): unique(org_id, contact_phone) + unique(org_id, contact_email) em leads. Insert duplicado falha — app code precisa fazer lookup ANTES.
REGRA #5 (lookup ANTES de criar via WhatsApp): Webhook handler WhatsApp inbound: SELECT id FROM leads WHERE org_id=$1 AND contact_phone=$2. Se existe, append message à conversa do lead. Se não existe, criar lead novo com source='whatsapp_inbound'.
Patterns canônicos
Tabela leads
create table public.leads (
id uuid primary key default gen_random_uuid(),
org_id uuid not null references public.organizations(id) on delete cascade,
dept_id uuid references public.departments(id) on delete set null,
-- Contato
contact_name text not null,
contact_email text,
contact_phone text,
contact_company text,
-- Pipeline
stage text not null default 'lead'
check (stage in ('lead', 'qualified', 'proposal', 'negotiation', 'won', 'lost')
or stage like 'custom\_%'),
source text, -- 'whatsapp_inbound', 'website_form', 'manual', etc.
-- Ownership
owner_id uuid references auth.users(id) on delete set null,
-- Dados financeiros
expected_value numeric(12, 2),
expected_close_date date,
closed_at timestamptz,
closed_reason text,
-- Metadata
metadata jsonb not null default '{}'::jsonb,
created_at timestamptz not null default now(),
updated_at timestamptz not null default now(),
-- REGRA #4: dedup
unique (org_id, contact_phone),
unique (org_id, contact_email)
);
create index leads_org_stage_idx on public.leads (org_id, stage);
create index leads_org_owner_idx on public.leads (org_id, owner_id) where owner_id is not null;
create index leads_org_dept_idx on public.leads (org_id, dept_id) where dept_id is not null;
-- RLS: aplicar pattern multi-tenant-rls-hierarchy
alter table public.leads enable row level security;
create policy "leads_select_member" on public.leads
for select to authenticated
using (private.is_member_of(org_id));
create policy "leads_insert_with_permission" on public.leads
for insert to authenticated
with check (private.has_permission('create', 'leads', org_id));
create policy "leads_update_with_permission_or_owner" on public.leads
for update to authenticated
using (
private.has_permission('update', 'leads', org_id)
or owner_id = (select auth.uid())
)
with check (
private.has_permission('update', 'leads', org_id)
or owner_id = (select auth.uid())
);
create policy "leads_delete_admin" on public.leads
for delete to authenticated
using (private.has_role(org_id, 'admin') or private.has_role(org_id, 'owner'));
create policy "leads_super_admin_bypass" on public.leads
as permissive for all to authenticated
using (private.is_super_admin())
with check (private.is_super_admin());
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 · 345 lines · 46 tokens per session scan A 32dcd8d787d2
crm-lead-pipeline-patterns is a skill published in the GitHub repository luanpdd/kit-mcp (5 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 2,965 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
360-feedback-system
360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or Notion on request. Use for 360 reviews or peer feedback cycles.
alumni-re-hire-tracker
Alumni and re-hire register: former role, last working day, re-hire eligibility, current employer and re-engagement date, as CSV, SQL, JSON Schema or Notion on request. Use for alumni outreach.
announcement-board
Announcement board: author, category, department, priority, audience, publish and expiry dates, status and acknowledgements, as CSV, SQL, JSON Schema or Notion on request. Use for internal notices.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
product-direction
Judges feature requests, feature pull requests and your own proposals against a repository's written product direction, gives a cited verdict, and records each new no. Use when triaging, labelling or replying to a feature request or a feature pull request, including as an autonomous triage agent; when asked whether a…