@xerg/cli 0.1.6 → 0.1.8

package/README.md

@@ -1,8 +1,10 @@
 # xerg
 
-Audit OpenClaw agent spend, waste, and before/after improvements.
+Audit OpenClaw workflows in dollars, compare fixes, and surface savings opportunities.
 
-Xerg audits OpenClaw workflows in dollars, not tokens. It reads your gateway logs and session transcripts, shows where money is leaking, classifies waste into five categories, and lets you re-run the same audit with `--compare` so you can see what changed after a fix.
+Xerg audits OpenClaw workflows in dollars, not tokens. It reads your gateway logs and session transcripts, surfaces five spend categories across confirmed waste and savings opportunities, and lets you re-run the same audit with `--compare` so you can see exactly what changed after a fix.
+
+Everything runs locally by default. No account is required for local audits. No data leaves your machine unless you explicitly `--push` results to the Xerg API for a team dashboard.
 
 ## 30-second quick start
 
@@ -22,19 +24,25 @@ xerg audit
 
 ## Bundled skill
 
-The published `@xerg/cli` package includes the portable Xerg skill bundle at:
+The published `@xerg/cli` package includes the portable Xerg skill bundle inside the installed package at:
+
+```text
+skills/xerg/SKILL.md
+```
+
+For a local project install, that usually resolves to:
 
 ```text
 node_modules/@xerg/cli/skills/xerg/SKILL.md
 ```
 
-That file is a packaged copy of the canonical repo skill at [`skills/xerg/SKILL.md`](../../skills/xerg/SKILL.md). Use it if your agent platform imports skills from disk; installing the npm package does not automatically register the skill with every agent product.
+For a global install, the same file lives inside the global npm package directory instead. That file is a packaged copy of the canonical repo skill at [`skills/xerg/SKILL.md`](../../skills/xerg/SKILL.md). Use it if your agent platform imports skills from disk; installing the npm package does not automatically register the skill with every agent product.
 
 ## Supported runtime
 
-`@xerg/cli` supports Node `20`, `22`, and `24`.
+`@xerg/cli` supports Node `22` and `24`.
 
-If you are developing in this repo, `.nvmrc` still pins the default local toolchain to Node `24.14.0`.
+If you are developing or releasing from this repo, `.nvmrc` pins the default toolchain to Node `24.14.0`.
 
 ## Sample output
 
@@ -84,7 +92,7 @@ xerg audit --since 24h --compare
 
 - Local machine: yes
 - VPS or remote server: yes
-- If OpenClaw runs remotely, SSH into the machine where the logs live and run Xerg there
+- If OpenClaw runs remotely, you can audit it from your local machine with `xerg audit --remote user@host`
 - Or point Xerg at exported files directly with flags
 
 Remote prerequisites:
@@ -134,7 +142,8 @@ Example `~/.xerg/config.json`:
 
 - Total spend by workflow and model, in dollars
 - Observed vs. estimated cost (always labeled)
-- Structural waste: retry, context bloat, loop, downgrade candidates, idle
+- Confirmed waste: retry, loop
+- Savings opportunities: context bloat, downgrade candidates, idle
 - Savings recommendations with suggested A/B tests
 - Before/after deltas on re-audit
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@xerg/cli",
-  "version": "0.1.6",
-  "description": "Audit OpenClaw agent spend, waste, and before/after improvements.",
+  "version": "0.1.8",
+  "description": "Audit OpenClaw workflows in dollars, compare fixes, and surface savings opportunities.",
   "keywords": ["ai", "agents", "finops", "llm", "openclaw", "cost", "cli"],
   "homepage": "https://xerg.ai",
   "repository": {
@@ -30,7 +30,7 @@
     }
   },
   "engines": {
-    "node": ">=20 <25"
+    "node": ">=22 <25"
   },
   "scripts": {
     "prebuild": "node ../../scripts/sync-cli-skill.mjs",

package/skills/xerg/SKILL.md

@@ -1,13 +1,23 @@
 ---
 name: xerg
-description: Audit OpenClaw agent spend in dollars. Use for local or remote audits, before/after comparisons, CI threshold gates, and machine-readable recommendations.
+description: Audit OpenClaw workflows in dollars. Local-first audits with compare mode, remote and Railway support, CI gates, and structured recommendations.
 ---
 
 # Xerg
 
 Use `xerg` if it is already installed. If not, use `npx @xerg/cli` with the same arguments.
 
-Xerg audits OpenClaw spend in dollars and surfaces both confirmed waste and savings opportunities. It can analyze local files, pull remote sources over SSH or Railway, compare against prior local snapshots, and optionally push audit summaries to the Xerg API.
+Xerg audits OpenClaw workflows in dollars, not tokens. It reads gateway logs and session transcripts, surfaces five spend categories across confirmed waste and savings opportunities, and helps you measure fixes with `--compare`.
+
+Local audits need no account. No data leaves your machine unless you explicitly `--push` results to the Xerg API.
+
+## Quick Start
+
+```bash
+xerg doctor
+xerg audit
+xerg audit --compare
+```
 
 ## Inputs
 
@@ -180,6 +190,7 @@ Before finalizing work that used Xerg:
 - If `--compare` was used, confirm that it compared against a compatible stored snapshot
 - If no data was found, run `xerg doctor` or use explicit source flags rather than guessing
 - Say whether results were pushed to the Xerg API
+- Distinguish confirmed waste (`retry-waste`, `loop-waste`) from directional opportunities (`context-outlier`, `idle-spend`, `candidate-downgrade`)
 
 ## Notes