LeadMagicLeadMagic/leadmagic-skills/AGENTS.md

leadmagic-skills

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

Reviewed: 2026-10-20 Guidance for AI agents editing or using this repository. Official product skills + Claude Code plugin so agents can call LeadMagic correctly: This repo does not document how LeadMagic's own apps are built. Claude Code names this plugin's MCP tools mcp__plugin_leadmagic_leadmagic__<tool> (hand-added server: mcp__leadmagic__<tool>). Hook matchers and agent tools grants must cover both. Router: leadmagic. Setup: connect-leadmagic. Focused: api-auth-credits, email-enrichment, people-search, people-enrichment, company-enrichment, company-search, job-search, jobs-hiring-intent, ads-intelligence, bulk-jobs, sheets, analytics-observability, outbound-recipes, mcp-integration.

Reads credentials

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- llms.txtllms.txt
- ads-intelligenceSkill
- analytics-observabilitySkill
- api-auth-creditsSkill
- bulk-jobsSkill
- company-enrichmentSkill
- company-searchSkill
- connect-leadmagicSkill
- email-enrichmentSkill
- job-searchSkill
- jobs-hiring-intentSkill
- leadmagicSkill
- mcp-integrationSkill
- outbound-recipesSkill
- people-enrichmentSkill
- people-searchSkill
- sheetsSkill

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Follow Claude skill authoring best practices.
line 47

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

AGENTS.md — LeadMagic Skills & Plugin

Reviewed: 2026-10-20

Guidance for AI agents editing or using this repository.

Purpose

Official product skills + Claude Code plugin so agents can call LeadMagic correctly:

REST API (https://api.leadmagic.io, X-API-Key) — the complete endpoint surface
Hosted MCP (https://mcp.leadmagic.io/mcp, OAuth)
Credits, plans, rate limits, and safe integration patterns
Bulk jobs / CSV uploaders (/bulk/*)
Sheets (Sheet Enrichment) — getting started in the app, then driving live sheets over MCP: enrichment, formula, AI and API columns, recipes
Outbound-system recipes (commands + outbound-recipes skill)

This repo does not document how LeadMagic's own apps are built.

Layout

Path	What
`skills/*/SKILL.md`	16 product and setup skills (also consumed standalone via `npx skills add`)
`skills/leadmagic/references/`	Endpoint quickref, plans & limits, recipes, learnings
`skills/sheets/references/`	Sheets tool catalog, recipe format, formulas + AI on OpenRouter, sheet ideas
`.claude-plugin/plugin.json`	Plugin manifest (skills + commands + agents + hooks + MCP)
`commands/*.md`	14 recipe slash commands (`/leadmagic:<name>`)
`agents/*.md`	`leadmagic-outbound`, `leadmagic-bulk`
`hooks/` + `scripts/approval-policy.sh`	PreToolUse policy: auto-allows reads, single-record lookups, and preview calls; asks once on the token-carrying call of bulk, paid sheet run, import, push, and delete tools, and on every call of other state-changing tools (cancel, pause, update, add, restore, rerun, export, create, configure, reorder, extract). Every paid sheet run, including small samples and AI billed to the user's own provider, requires a quote and explicit approval. The public `LeadMagic/leadmagic-claude-plugin` repository owns the Claude plugin hook; coordinate policy changes between these standalone public repositories

Claude Code names this plugin's MCP tools mcp__plugin_leadmagic_leadmagic__<tool> (hand-added server: mcp__leadmagic__<tool>). Hook matchers and agent tools grants must cover both.

Skill map

Router: leadmagic. Setup: connect-leadmagic. Focused: api-auth-credits, email-enrichment, people-search, people-enrichment, company-enrichment, company-search, job-search, jobs-hiring-intent, ads-intelligence, bulk-jobs, sheets, analytics-observability, outbound-recipes, mcp-integration.

Editing rules

No secrets — examples use $LEADMAGIC_API_KEY only. No customer PII or raw enrichment payloads.
Docs are the public source of truth — leadmagic.io/docs. Credit costs and rate limits in this repo are synced from the live API contract; when the API changes, update references/leadmagic-api-quickref.md and references/plans-and-limits.md first, then the focused skills.
Frontmatter: name matches folder; description states what + when (third person); SKILL.md ≤ 200 lines preferred, 500 max; tags under metadata.tags; bump metadata.version on content changes.
Plan awareness is mandatory in any skill that touches the v3 search surfaces (credit-free on Professional/Ultimate, per-row elsewhere).
No third-party brand names anywhere in skills/ — use B2B Profile wording; profile_url in examples (bare /in/{slug} forms normalize). Allowed exceptions: the hosted MCP tool id the validator whitelists, and AI model providers a user connects their own key for in the Sheets Vault (e.g. OpenRouter setup and vendor/model ids).
Commands must state cost and get confirmation before credit-consuming runs; free preflights never prompt.
Validate before PR: ./scripts/validate.sh and claude plugin validate ..
Follow Claude skill authoring best practices.

Related public repos

LeadMagic/leadmagic-openapi — OpenAPI snapshot (may lag the live contract)
LeadMagic/gtm-skills — GTM strategy skills (keep product docs here, strategy there)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free