tc

tc is a command for Claude Code from ricneves-ai/flowgrammers-skills. It costs 45 tokens per session (1,451 once invoked), scanned A, original, MIT.

A technical-change tracker that stores structured records for engineering changes across sessions. It supports statuses, affected files, handoffs, resuming previous work, and generated summaries or dashboards.

In plain words
What is it for?
Use it to initialize tracking, create and update change records, check status, resume work, close deployed changes, and export summaries.
Why use it?
It preserves the context of an engineering change when work moves between sessions or people. This reduces the risk of losing decisions, status, or next steps.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 engineering/tc-tracker/scripts/tc_init.py --root . --json.

Good fit Use it to initialize tracking, create and update change records, check status, resume work, close deployed changes, and export summaries.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skills
agentmods
npx agentmods add commands/ricneves-ai/flowgrammers-skills/tc

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 tc

README.md
[![agentmods](https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/tc/github.svg)](https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/tc)
Your own site
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/tc"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/tc/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 tc

Your own site · 80×15
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/tc"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/tc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,451 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 $0.00045 $0.01451
Opus 5 $0.00023 $0.00726
Sonnet 5 $0.00009 $0.00290
Haiku 4.5 $0.00005 $0.00145

Measured 9d ago against content hash a3a28faf9bb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tc 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 9d 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/tc.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tc — Rastreador de Mudanças Técnicas

Despacha um comando de TC (Technical Change). Argumentos: $ARGUMENTS.

Se $ARGUMENTS estiver vazio, exibe este menu e para:

/tc init                       Inicializa o rastreamento de TC neste projeto
/tc create <nome>              Cria um novo registro TC
/tc update <tc-id> [...]       Atualiza campos, status, arquivos, handoff
/tc status [tc-id]             Exibe um TC ou o resumo do registro
/tc resume <tc-id>             Retoma um TC de uma sessão anterior
/tc close <tc-id>              Transiciona um TC para implantado
/tc export                     Re-renderiza artefatos derivados
/tc dashboard                  Re-renderiza o resumo do registro

Caso contrário, analisa $ARGUMENTS como <subcomando> <resto> e despacha para o protocolo correspondente abaixo. Todos os scripts ficam em engineering/tc-tracker/scripts/.

Subcomandos

init

python3 engineering/tc-tracker/scripts/tc_init.py --root . --json

Se status for already_initialized, reporta estatísticas atuais e para. Caso contrário, reporta o que foi criado e sugere /tc create <nome> como próximo passo.

create <nome>

  1. Interpreta <nome> como slug em kebab-case. Se ausente, pede ao usuário.
  2. Solicita (uma pergunta por vez):
    • Título (5–120 chars)
    • Escopo: feature | bugfix | refactor | infrastructure | documentation | hotfix | enhancement
    • Prioridade: critical | high | medium | low (padrão medium)
    • Resumo (10+ chars)
    • Motivação
  3. Executa:
    python3 engineering/tc-tracker/scripts/tc_create.py --root . \
      --name "<slug>" --title "<título>" --scope <escopo> --priority <prioridade> \
      --summary "<resumo>" --motivation "<motivação>" --json
    
  4. Reporta o ID do novo TC e o caminho para o registro.

update <tc-id> [intenção]

  1. Se <tc-id> estiver ausente, lista TCs ativos e pergunta qual.
  2. Determina a intenção do usuário a partir de linguagem natural:
    • Mudança de status--set-status <estado> com --reason "<motivo>"
    • Adicionar arquivos--add-file caminho[:ação]
    • Adicionar teste--add-test "<título>" --test-procedure "<passo>" --test-expected "<resultado>"
    • Atualizar handoff--handoff-progress, --handoff-next, --handoff-blocker, --handoff-context
    • Adicionar nota--note "<texto>"
    • Adicionar tag--tag <tag>
  3. Executa:
    python3 engineering/tc-tracker/scripts/tc_update.py --root . --tc-id <tc-id> [flags] --json
    
  4. Se código de saída não for zero, exibe o erro verbatim. Não repita cegamente.

Read the full file on GitHub · 120 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. 9d ago First seen · 120 lines · 0 tokens per session scan A a3a28faf9bb5

Subscribe to this mod's changes

tc is a command published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,451 once invoked, about $0.0002 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.