hot

hot is a command for coding agents from vynazevedo/first-plan. It costs 25 tokens per session (515 once invoked), scanned A, original, MIT.

A Git activity heatmap that shows which files and folders have received the most recent commits, meaning code changes.

In plain words
What is it for?
Use it to inspect recent activity over a chosen number of days, find heavily changed areas, and spot old folders with no commits for a long time.
Why use it?
It helps you quickly see where the team is working now and which parts of the project have gone quiet.

Command

Part of the fp plugin — 19 skills, 19 commands, 4 agents, 1 hook shipped together

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.

agentmods
npx agentmods add commands/vynazevedo/first-plan/hot
Clone the repo
git clone --depth 1 https://github.com/vynazevedo/first-plan

Or install fp, the plugin that ships this one along with the rest of its 19 skills, 19 commands, 4 agents, 1 hook.

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 hot

README.md
[![agentmods](https://agentmods.dev/badge/commands/vynazevedo/first-plan/hot.svg)](https://agentmods.dev/commands/vynazevedo/first-plan/hot)
Your own site
<a href="https://agentmods.dev/commands/vynazevedo/first-plan/hot"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/hot.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.00515
Opus 5 $0.00013 $0.00258
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 4d ago against content hash 79b7d4aa13bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hot 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 4d 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.

commands/hot.md · 69 lines

What it actually says

/fp:hot

Heatmap de atividade.

Argumentos

$ARGUMENTS:

  • vazio: window de 30 dias (default)
  • --days N: window customizado (e.g., --days 7, --days 90)

Workflow

Passo 1 - Pre-flight

Verificar git repo. Verificar .first-plan/01-topology/activity.md existe.

Passo 2 - Render

Para window default (30 dias): ler activity.md.

Para window customizado: rerun inline:

git log --since="N days ago" --name-only --pretty=format: | grep -v '^$' | sort | uniq -c | sort -rn | head -20

Passo 3 - Apresentar

Hot zones - últimos <N> dias

Top 20 arquivos:
  47 internal/payment/charge.go         (refator em curso?)
  31 internal/handler/order.go          
  28 src/components/Cart.tsx            
  ...

Top 20 pastas:
  127 internal/payment/                 hot zone ⚠
   89 src/components/                   hot zone ⚠
   67 internal/handler/                 
  ...

Hot zones (>= 10 commits):
- internal/payment/    - 127 commits (intensa atividade)
- src/components/      - 89 commits (provavelmente UI sendo polida)

Frozen zones (sem commits > 180 dias):
- internal/legacy/     - silencioso ha 8 meses
- pkg/oldauth/         - silencioso ha 14 meses (candidato dead code?)

Implicações:
- Padrões em hot zones podem estar em transição - olhar últimos commits, não histórico antigo
- Frozen zones têm padrões antigos e estáveis
- Mexer em hot zones = alta chance de conflito com PRs em flight (ver /fp:in-flight)

Passo 4 - Conexão com outras camadas

Sugestões automáticas:

  • Se algum hot zone tem feature DRIFTED associada: alertar
  • Se algum hot zone tem ownership claro: mostrar dono
  • Se algum hot zone tem PR em flight: linkar
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. 4d ago First seen · 69 lines · 25 tokens per session scan A 79b7d4aa13bb

Subscribe to this mod's changes

hot is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 515 once invoked, about $0.0001 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 2026-08-30.