@agent-crm/cli 0.0.3 → 0.0.5

package/README.md

@@ -4,7 +4,7 @@
 
 </div>
 
-Claude is running your GTM and your leads live in CSVs. Spreadsheets fall apart around 30 deals in: you lose track of who said what, what's open, and what's next. CRMs solve that, but they were built for humans clicking through UIs, not agents writing SQL.
+Claude is running your GTM and your leads live in CSVs. Spreadsheets fall apart around 30 deals in: you lose track of who said what, what's open, and what's next. CRMs solve that, but they were built for humans clicking through UIs, not agents reading and writing it on your behalf.
 
 Plug Claude into your CRM via MCP and the schema torches your context, every action is a network round-trip, and you blow through your usage limits. Salesforce and HubSpot are shipping their own CLIs, but they end at the deal record — the scrapes, enrichment runs, and half-cleaned lists that fed it live somewhere else. You can't replay how a deal moved through stages, see what your last scrape pulled in and what it didn't clean up, or pick up where last weekend's list-building session left off.
 
@@ -22,7 +22,7 @@ Agents work best on files. Agent CRM is a portable `.acrm` file your agent can q
 
 ## What's in a `.acrm` file?
 
-A `.acrm` file is a **SQLite database** with a change-history layer ([Lix](https://lix.dev)) on top. That means:
+A `.acrm` file is a **SQLite database** with a [change-history layer](https://lix.dev) on top. That means:
 
 - **No proprietary format.** Open it with any SQLite client (`sqlite3 pipeline.acrm`) and your data is right there in standard tables.
 - **Every write is a versioned checkpoint.** Like git for your CRM — branch to run an experiment, diff to see what changed, revert if Claude mangles a row.
@@ -47,19 +47,19 @@ claude --dangerously-skip-permissions
 Create an .acrm file
 
 ```bash
-acrm init pipeline.acrm
+! acrm init pipeline.acrm
 ```
 
 Then import your CSVs
 
 ```bash
-acrm import csv ./leads.csv
+! acrm import csv ./leads.csv
 ```
 
-And query the file any time with:
+And query the file any time:
 
 ```bash
-acrm execute "select * from people limit 5;"
+! acrm execute "select object_slug, count(*) as n from acrm_record group by object_slug"
 ```
 
 ## Why Agent CRM
@@ -95,7 +95,7 @@ description: Pull a Granola transcript, resolve the person in .acrm, and log the
 ## Steps
 
 1. **Resolve the person** with a SQL lookup against `pipeline.acrm`:
-   `acrm execute "SELECT DISTINCT record_id FROM acrm_value WHERE object_slug = 'people' AND attribute_slug = 'email_addresses' AND active_until IS NULL AND normalized_key = ?" '["<email>"]' --json`
+   `acrm execute "SELECT DISTINCT record_id FROM acrm_value WHERE object_slug = 'people' AND attribute_slug = 'email_addresses' AND active_until IS NULL AND normalized_key = $1" '["<lowercased-email>"]' --json`
 
 2. **Find the Granola meeting** via `mcp__granola__list_meetings`. Filter
    to meetings where the person's name appears in the title or

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@agent-crm/cli",
-  "version": "0.0.3",
-  "description": "Headless CRM for claude code — versioned, queryable, scriptable",
+  "version": "0.0.5",
+  "description": "Agent CRM: Headless CRM for claude code",
   "type": "module",
   "bin": {
     "acrm": "dist/bin/acrm.js"