A B2B data-enrichment service for adding verified work contacts, LinkedIn profiles, and company details to business records. It includes a source citation and confidence level for each field and can write results back to a CRM.

Use it to search for target companies or contacts, enrich CRM records, find work emails, research accounts, and write the results back to a CRM.

It reduces the manual work of finding people and company information and makes the evidence behind each data field visible.

abm-dev — Skill for Claude Code by abm-dev-git/abm-mcp

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 abm-dev-git/abm-mcp --skill abm-dev

Clone the repo

git clone --depth 1 https://github.com/abm-dev-git/abm-mcp

Made for: Claude Code.

Or install abm-dev, the plugin that ships this one along with the rest of its 1 skill.

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/abm-dev-git/abm-mcp/abm-dev/github.svg)](https://agentmods.dev/skills/abm-dev-git/abm-mcp/abm-dev)

Your own site

<a href="https://agentmods.dev/skills/abm-dev-git/abm-mcp/abm-dev"><img src="https://agentmods.dev/badge/skills/abm-dev-git/abm-mcp/abm-dev/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/abm-dev-git/abm-mcp/abm-dev"><img src="https://agentmods.dev/badge/skills/abm-dev-git/abm-mcp/abm-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,357 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	$0.00067	$0.02357
Opus 5.5	$0.00027	$0.00943
Sonnet 5.5	$0.00013	$0.00471
Haiku 4.5	$0.00007	$0.00236

Measured 1mo ago against content hash 47ab19d9eca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

abm-dev 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.

claude-plugin/skills/abm-dev/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

abm.dev — B2B enrichment for agents

abm.dev turns an email, a name + company, or a LinkedIn URL into ~89 canonical fields per record (43 person + 46 company), each with a source citation and a confidence score, synthesised from ~10 data sources — and writes the results back to your CRM.

Connect

MCP (preferred): https://mcp.abm.dev/mcp — OAuth sign-in on first use. One-click from Claude: https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=abm.dev&connectorUrl=https%3A%2F%2Fmcp.abm.dev%2Fmcp
REST API: https://api.abm.dev with the X-API-Key header — mint a key at https://abm.dev/settings/api-keys. Same verbs: POST /v2/enrich, POST /v2/search, POST /v2/source.
CLI: npx -y @abmdev/cli@latest init --all -k <API_KEY>

The core loop (match → enrich → write back)

Match the record in the CRM: search_companies / search_contacts. Filters are EXACT-match — match on domain/email, not display names ("Saffery" will not match "Saffery LLP"). No match? create_company / create_contact.
Enrich with the CRM id threaded through: create_enrichment { type, input: { company_name, domain, crm_id } } → returns a job_id (async, commonly 3–8 min). Add refresh: true to force a from-scratch run when the record was enriched recently. Poll get_enrichment every 30–60s until completed (a processing status with 0 fields is normal — do not give up before ~10 min), then read values with get_enrichment_fields and provenance with get_enrichment_sources.
Write back: preview_writeback shows the per-field keep/use diff; then approve_enrichment (REAL CRM mutation). If the preview shows no/wrong matched record, pass crm_entity_id on approve.

Finding people (async search)

Read the full file on GitHub · 138 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.

1mo ago First seen · 138 lines · 67 tokens per session scan A 47ab19d9eca4

Subscribe to this mod's changes

abm-dev is a skill published in the GitHub repository abm-dev-git/abm-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 2,357 once invoked, about $0.0003 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 2026-08-31.

ABM Marketing and SEO ai-agents b2b-data enrichment gtm mcp

deepline-ads-audiences

Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…

getaero-io/gtm-eng-skills · 133 tokens

deepline-analytics

Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of…

getaero-io/gtm-eng-skills · 115 tokens

deepline-engine

Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.

getaero-io/gtm-eng-skills · 43 tokens

deepline-gtm

GTM prospecting, enrichment, outreach, and Deepline Play work/audits. Providers…

getaero-io/gtm-eng-skills · 333 tokens

deepline-plays-review

Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration. Triggers on “put this run in a Sheet,” “review these results,” “read my feedback,” “make this a standing rule,” “never regress on this…

getaero-io/gtm-eng-skills · 121 tokens

deepline-start

Interview a user to discover a concrete GTM problem or manual task, recommend the right installed Deepline skill, prebuilt Play, recipe, or tool, confirm the plan and org, then start the chosen workflow. Use only when the user explicitly invokes deepline-start.

getaero-io/gtm-eng-skills · 58 tokens