custo-fase

custo-fase is a command for Claude Code from luanpdd/kit-mcp. It costs 50 tokens per session (1,469 once invoked), scanned A, original, MIT.

A command that estimates how much Claude Code usage was associated with a project phase. It compares file times, recorded completion times, Git history, and usage logs to identify the likely time window.

In plain words
What is it for?
Use it to inspect or optionally save cost estimates for phases recorded in a planning directory.
Why use it?
It connects usage cost to a specific phase so teams can review spending by piece of work and see how reliable the estimate is.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to inspect or optionally save cost estimates for phases recorded in a planning directory.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/custo-fase
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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

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.

agentmods badge for custo-fase

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/custo-fase/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/custo-fase)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/custo-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/custo-fase/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.

agentmods 80×15 button for custo-fase

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/custo-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/custo-fase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01469
Opus 5 $0.00025 $0.00734
Sonnet 5 $0.00010 $0.00294
Haiku 4.5 $0.00005 $0.00147

Measured 5d ago against content hash ce4162a67afc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

custo-fase 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 5d 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.

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.

kit/commands/custo-fase.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inferência de janela temporal:

  • started_at ← mtime do arquivo SPEC.md em .planning/phases/<phase_id>-*/.
  • ended_atcompleted_at de .planning/STATE.md (se a fase foi concluída) OU null se ainda ativa.
  • Cross-ref com git log --since/--until para apertar bordas.

correlation_confidence:

  • high: SPEC.md mtime + completed_at + commits no intervalo (3/3 sinais).
  • medium: 2/3 sinais.
  • low: apenas mtime do dir OU detecção de rebase recente (reflog) que invalidaria bordas.
  • unknown: fase não encontrada em .planning/phases/.

Lê: .planning/phases/<id>-*/SPEC.md, .planning/STATE.md, git log, JSONLs do Claude Code.

Cria/Atualiza: nada por default. Com --persist, grava em .planning/costs/<ts>-cost-phase.json.

Após: o user vê custo da fase + correlation_confidence + correlation_signals para auditar a confiança no número.

Disambiguation: sobre USD/tokens reais da fase, não sobre métricas de progresso da fase. Para progresso → ver STATE.md direto. Para custo financeiro → este comando. Ver skill cost-tracking.

  • <phase_id>obrigatório. ID da fase (ex: 172). Sem o ID, o comando emite erro e sugere /listar-fases.
  • --refresh-pricing — opt-in models.dev fallback.
  • --persist — salva snapshot.

Cross-reference: SSOT do algoritmo de correlação é src/core/cost/aggregate-phase.js + skill cost-tracking. Confidence levels documentados no SPEC 172.

1. Parsear argumentos

PHASE_ID=$(echo "$ARGUMENTS" | awk '{for(i=1;i<=NF;i++) if($i !~ /^--/) {print $i; exit}}')
REFRESH=$(echo "$ARGUMENTS" | grep -oE -- '--refresh-pricing' | head -1)
PERSIST=$(echo "$ARGUMENTS" | grep -oE -- '--persist' | head -1)

if [ -z "$PHASE_ID" ]; then
  echo "Uso: /custo-fase <phase_id> [--refresh-pricing] [--persist]"
  echo "Exemplo: /custo-fase 172"
  exit 1
fi

Read the full file on GitHub · 139 lines

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. 5d ago First seen · 139 lines · 50 tokens per session scan A ce4162a67afc

Subscribe to this mod's changes

custo-fase is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,469 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-03.