What is context-budget-audit?

An audit of the context space used by an AI coding setup. It measures the token use of agents, skills, rules, MCP connections, and CLAUDE.md files, then identifies bulky or repeated components.

Use it after adding tools or instructions, when a session degrades, or before expanding the setup. It produces an optimisation report and three leading recommendations.

Large context can make conversations slower and responses less reliable. The audit shows where space is being used and ranks possible reductions.

context-budget-audit — Skill for Claude Code by findscripter

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.

Any agent

npx skills add findscripter/everything-skills --skill context-budget-audit

Clone the repo

git clone --depth 1 https://github.com/findscripter/everything-skills

Made for: Claude Code.

Or install 00-meta, the plugin that ships this one along with the rest of its 43 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/findscripter/everything-skills/context-budget-audit/github.svg)](https://agentmods.dev/skills/findscripter/everything-skills/context-budget-audit)

Your own site

<a href="https://agentmods.dev/skills/findscripter/everything-skills/context-budget-audit"><img src="https://agentmods.dev/badge/skills/findscripter/everything-skills/context-budget-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/findscripter/everything-skills/context-budget-audit"><img src="https://agentmods.dev/badge/skills/findscripter/everything-skills/context-budget-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,275 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00141	$0.02275
Opus 5.5	$0.00056	$0.00910
Sonnet 5.5	$0.00028	$0.00455
Haiku 4.5	$0.00014	$0.00228

Measured today against content hash a6c892475a58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-budget-audit scanned grade A with 1 finding 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 today.

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.

Reads MCP configurationlowAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

| MCP | `.mcp.json` / 活跃 MCP 配置 | 服务器数 + 工具总数；每工具 schema ≈ **500 token** | 单服务器 >20 工具；包装 `gh`/`git`/`npm`/`supabase`/`vercel` 等简单 CLI 的服务器 |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

00-meta/context-budget-audit/SKILL.md · 142 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

today First seen · 142 lines · 141 tokens per session scan A a6c892475a58

Subscribe to this mod's changes

context-budget-audit is a skill published in the GitHub repository findscripter/everything-skills (11 stars, last pushed today), with no licence file. It adds 141 tokens to every session and 2,275 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-12.

Analytics and metrics LLM Memory and context agent-skills ai-agents chinese mcp token 公众号

context-budget-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-budget-auditfindscripter/everything-skills	Skill	11	today	none	A	141	Claude Code
nuphus-modulesmrpulor-gh/nuphus	Skill	103	yesterday	Apache-2.0	A	0	Claude Code, Codex
context-managementkangarooking/system-prompt-skills	Skill	224	6mo ago	MIT	A	136	Claude Code, Codex
Apple Notesagentic-in/elephant-agent	Skill	586	2mo ago	none	A	31	Claude Code, Codex
GIF Searchagentic-in/elephant-agent	Skill	586	2mo ago	none	A	26	Claude Code, Codex
cocos-creator-drawcallWade-DevCode/awesome-coding-skills-cn	Skill	7	5mo ago	MIT	A	32	Claude Code, Codex
cocos-creator-hotupdateWade-DevCode/awesome-coding-skills-cn	Skill	7	5mo ago	MIT	A	32	Claude Code, Codex