@nightlab-agent/subagent-spend 0.8.0 → 0.8.2

package/.claude-plugin/marketplace.json

@@ -8,7 +8,7 @@
       "name": "subagent-spend",
       "source": "./",
       "description": "A spend cap for interactive sessions, and per-subagent tokens, rate-limit windows, context fill, cost, steps, tool calls and tool errors of a Claude Code session, in a notice under the prompt, local files and panes (the usage pane not yet seen on a screen).",
-      "version": "0.8.0",
+      "version": "0.8.2",
       "category": "productivity"
     }
   ],

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "subagent-spend",
-  "version": "0.8.0",
+  "version": "0.8.2",
   "description": "A spend cap for interactive sessions, and per-subagent tokens, rate-limit windows, context fill, cost, steps, tool calls and tool errors of a Claude Code session, in a notice under the prompt, local files and panes (the usage pane not yet seen on a screen).",
   "author": {
     "name": "Nightlab"

package/CHANGELOG.md

@@ -2,6 +2,17 @@
 
 The form is Keep a Changelog; versions follow SemVer.
 
+## 0.8.2 - 2026-11-03
+
+### Changed
+- README: the opening says what an unwatched long job costs before what the plugin does, and the spend cap
+  picture (seen 2026-10-31) is on the first screen. No code change.
+
+## 0.8.1 - 2026-11-02
+
+### Changed
+- README: the opening lines name the spend cap and link its section. No code change.
+
 ## 0.8.0 - 2026-11-01
 
 ### Added

package/README.md

@@ -1,14 +1,21 @@
 # subagent-spend
 
-Claude Code meters: subagent tokens, usage limits and turn counts.
+Hand Claude Code a long job and its subagents keep spending tokens while you
+are away. This plugin puts what they used, your usage limits and a count of
+steps and tool calls in one line under the prompt. If you set a dollar cap, once a session's cost
+reaches it no new request goes out ([Spend cap](#spend-cap)).
 
-This mod (a plugin that adds behaviour to Claude Code) shows three things in
-one line under the prompt and writes each to a small local file a script can
-read: the tokens each subagent used, summed per subagent; the usage limits;
-and a running count of steps, tool calls and tool errors. If you set one, a
-spend cap stops sending requests once an interactive session's cost reaches it. It also has side
-panes: the subagent pane is seen below; the Usage pane is not yet seen on a
-real screen. Nothing leaves your machine.
+Install at the Claude Code prompt (more under [Install](#install)):
+
+```
+/plugin install subagent-spend --marketplace nightlab-agent/subagent-spend
+```
+
+![Claude Code with a $0.10 cap: asked to read every file and describe each, Claude reads four files; the next step is answered by the plugin's line saying the session cost $0.11 of the $0.10 cap and no request was sent](https://raw.githubusercontent.com/nightlab-agent/subagent-spend/bcb368556c20a40c62ce952574e5a1bec5210923/docs/spend-cap-midturn.png)
+
+The spend cap, seen on 2026-10-31: a $0.10 cap, and the next step got the
+line above instead of a request ([Spend cap](#spend-cap)). The line under
+the prompt, after three subagents ran:
 
 ![Claude Code after three subagents ran: the subagent pane lists the three with their turns and tokens, and the line under the prompt reads subagents 3, tok 218k, then the usage windows, cost and step counts](https://raw.githubusercontent.com/nightlab-agent/subagent-spend/c676e8c3462af96a5b8d581b0adb479fa706f470/docs/preview.png)
 
@@ -18,6 +25,15 @@ fits. `tok` counts every token the subagents sent and got, cache reads
 included, so it is larger than the token figure each subagent reports when it
 returns. At 120 columns the same session drew no pane and the end of the line
 was cut with "…".
+A Short of it, redrawn large: https://www.youtube.com/shorts/F_NQxGPtnco
+
+This mod (a plugin that adds behaviour to Claude Code) shows three things in
+one line under the prompt and writes each to a small local file a script can
+read: the tokens each subagent used, summed per subagent; the usage limits;
+and a running count of steps, tool calls and tool errors. If you set one, a
+spend cap stops sending requests once an interactive session's cost reaches it. It also has side
+panes: the subagent pane is seen above; the Usage pane is not yet seen on a
+real screen. Nothing leaves your machine.
 
 ## Install
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@nightlab-agent/subagent-spend",
-  "version": "0.8.0",
-  "description": "Claude Code mod: a spend cap for interactive sessions, and per-subagent tokens, rate-limit windows, context fill, cost, steps, tool calls and tool errors of a session, in a notice under the prompt, local files and panes (the usage pane not yet seen on a screen).",
+  "version": "0.8.2",
+  "description": "Claude Code plugin: a spend cap for interactive sessions, and per-subagent tokens, rate-limit windows, context fill, cost, steps, tool calls and tool errors of a session, in a notice under the prompt, local files and panes (the usage pane not yet seen on a screen).",
   "keywords": [
     "claude-code",
     "claude-code-mod",

package/subagent_spend.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""subagent-spend 0.8.0: attribute Claude Code token usage to each subagent.
+"""subagent-spend 0.8.2: attribute Claude Code token usage to each subagent.
 
   subagent_spend.py hook        SubagentStop hook: reads the hook JSON on stdin, sums the usage
                                 in the subagent transcript, appends one line to the session's rows file.