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.
npx skills add felvieira/claude-skills-fv --skill 49-context-budgetgit clone --depth 1 https://github.com/felvieira/claude-skills-fvWrote 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.
[](https://agentmods.dev/skills/felvieira/claude-skills-fv/49-context-budget)<a href="https://agentmods.dev/skills/felvieira/claude-skills-fv/49-context-budget"><img src="https://agentmods.dev/badge/skills/felvieira/claude-skills-fv/49-context-budget/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.
<a href="https://agentmods.dev/skills/felvieira/claude-skills-fv/49-context-budget"><img src="https://agentmods.dev/badge/skills/felvieira/claude-skills-fv/49-context-budget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00174 | $0.01863 |
| Opus 5 | $0.00087 | $0.00932 |
| Sonnet 5 | $0.00035 | $0.00373 |
| Haiku 4.5 | $0.00017 | $0.00186 |
Grade B, and why
context-budget scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find .claude/rules/ -name "*.md" | xargs wc -c 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 49 — Context Budget
Objetivo
Auditar o peso de contexto carregado em uma sessão Claude Code: quais skills/agents/MCP/rules/CLAUDE.md estão contribuindo para o overhead de tokens, quanto custa cada componente, e o que pode ser cortado ou adiado sem perder funcionalidade.
Distinção crítica:
- Skill 30 (
cost-tracker) → rastreia tokens/$ gastos em runtime (completions, tool calls) - Skill 49 (
context-budget) → audita tokens carregados no contexto antes de qualquer completion (system prompt, CLAUDE.md, rules, skills, MCP descriptions)
Quando usar
- Sessão com latência alta ou model degradation (possível context overflow)
- Repo novo com
.bot/— auditoria do que foi instalado - Antes de habilitar novo MCP server ou subagent
- Após instalar rules system path-scoped — verificar overhead real
- Quando
/savingsmostrar contexto inchado
Protocolo
Fase 0 — Identificar componentes carregados
Listar o que está no contexto da sessão:
1. CLAUDE.md (global + projeto)
2. .claude/rules/**/*.md (path-scoped — quais foram ativados?)
3. skills/ carregadas via Skill() nesta sessão
4. agents/ descrições (sempre presentes no system prompt)
5. MCP server descriptions (presentes para cada server ativo)
6. Arquivos abertos/lidos na sessão
7. Histórico de conversa acumulado
Fase 1 — Estimar peso por componente
Para cada componente, estimar tokens:
regra geral: ~4 chars por token (aproximação BPE)
- ler tamanho do arquivo em bytes
- tokens ≈ bytes / 4
- overhead real pode ser 10-20% maior (BPE não é linear)
Comando de varredura rápida:
# Peso dos arquivos de contexto fixo
find . -name "CLAUDE.md" -o -name "GLOBAL.md" | xargs wc -c 2>/dev/null
# Peso das rules ativas
find .claude/rules/ -name "*.md" | xargs wc -c 2>/dev/null
# Peso dos agents (sempre no system prompt)
find agents/ -name "*.md" | xargs wc -c 2>/dev/null
# Peso das skills (sob demanda — verificar quais foram invocadas)
find skills/ -name "SKILL.md" | xargs wc -c 2>/dev/null | tail -1
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.
- 2d ago Changed · +3 lines e26e325fcf05
- 9d ago First seen · 170 lines · 174 tokens per session scan B 28955161fbe4
context-budget is a skill published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 174 tokens to every session and 1,863 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.