context-budget

A measurement tool for the fixed startup information that Claude Code loads before working, including the space used by individual built-in tools.

In plain words
What is it for?
Use it to measure context usage, compare settings before and after changes, and keep a record of the measured differences.
Why use it?
It shows which settings or tools consume the available conversation context, so you can make informed configuration changes instead of guessing.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add melodic-software/claude-code-plugins
agentmods
npx agentmods add plugins/melodic-software/claude-code-plugins/context-budget
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

context-budget 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 yesterday.

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.

plugins/context-budget/.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "context-budget",
  "version": "0.6.14",
  "description": "Measure a Claude Code session's fixed startup context payload per item, on the consumer's machine at a pinned, version-stamped binary \u2014 including per-tool attribution of the built-in tool pools that /context reports only as lump sums, derived live by A/B bare-name-deny differencing with enforced comparability rules (skill-listing signature, one mode, one binary), an SDK-primary exact meter degrading to a version-aware headless /context parser and then to an honest structured error (never a wrong number), and a per-project measure-toggle-remeasure ledger under the plugin data directory recording every lever's real before/after delta. Report-only: prints exact config, applies nothing.",
  "author": {
    "name": "Melodic Software",
    "email": "[email protected]"
  },
  "license": "MIT",
  "userConfig": {
    "settings_write_ask_enabled": {
      "type": "boolean",
      "title": "Settings-write ask checkpoint",
      "description": "Kill switch for the PreToolUse hook that forces a permission prompt (permissionDecision ask) on any Write/Edit targeting a Claude Code settings surface",
      "default": true
    }
  },
  "keywords": [
    "context-window",
    "startup-payload",
    "token-budget",
    "tool-schemas",
    "measurement",
    "attribution",
    "ledger",
    "skill"
  ]
}
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.

  1. yesterday First seen · 30 lines scan A c951ebe0751e

Subscribe to this mod's changes

context-budget is a plugin published in the GitHub repository melodic-software/claude-code-plugins (12 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.