DQIII8: Command for Claude Code

.claude/commands/proyecto.md

proyecto is a command for Claude Code from senda-labs/DQIII8. It costs 32 tokens per session (503 once invoked), scanned A, original, MIT.

A command for declaring which project is currently active for time and cost tracking. It can show the active project, set one, or close the current declaration.

In plain words
What is it for?
Use it to select a valid project, check the current selection, end the selection, and let related time-tracking commands use that project automatically.
Why use it?
It prevents work logs from being assigned to the wrong project or requiring the project name every time.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument; mentions Claude Code.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is "") python3 bin/tools/project_ctl.py get ;;.

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/commands/proyecto.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 proyecto

README.md
[![agentmods](https://agentmods.dev/badge/commands/senda-labs/dqiii8/proyecto/github.svg)](https://agentmods.dev/commands/senda-labs/dqiii8/proyecto)
Your own site
<a href="https://agentmods.dev/commands/senda-labs/dqiii8/proyecto"><img src="https://agentmods.dev/badge/commands/senda-labs/dqiii8/proyecto/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 proyecto

Your own site · 80×15
<a href="https://agentmods.dev/commands/senda-labs/dqiii8/proyecto"><img src="https://agentmods.dev/badge/commands/senda-labs/dqiii8/proyecto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 $0.00032 $0.00503
Opus 5 $0.00016 $0.00251
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00050

Measured 9d ago against content hash a0d39e42d610, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

proyecto 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.

.claude/commands/proyecto.md · 50 lines

What it actually says

/proyecto — Declarar Proyecto Activo

Escribe una fila abierta en project_context (scope global), fuente de verdad que resolve_project() consulta desde los puntos de escritura de agent_actions (pre_tool_use.py, openrouter_wrapper.log_to_db(), pal/engine.py, y los hooks de sesion) cuando no hay project= explicito.

Uso

/proyecto                    # muestra el proyecto activo (scope global)
/proyecto football-value     # declara football-value como proyecto activo
/proyecto fin                # cierra la declaracion (vuelve a resolver por cwd/dqiii8-core)

Proyectos validos: cualquier directorio en my-projects/ + dqiii8-core. /proyecto <nombre-invalido> falla con la lista de proyectos conocidos.

/hora inicio sin argumento usa el proyecto resuelto por este comando en vez de requerir el nombre explicito cada vez.

Implementacion

Mapeo de argumentos: sin args -> get; fin -> end; cualquier otra cosa -> set <arg>.

cd /root/dqiii8
case "$1" in
  "") python3 bin/tools/project_ctl.py get ;;
  fin) python3 bin/tools/project_ctl.py end ;;
  *) python3 bin/tools/project_ctl.py set "$1" ;;
esac

Notas DQIII8

  • Version Telegram equivalente: /proyecto en dqiii8_bot.py (mismo project_context, declared_by='telegram').
  • Declarar via CLI en una sesion Claude Code no persiste automaticamente para otras sesiones/procesos hasta que estos re-consulten la DB via resolve_project() (bin/core/project_context.py) — no existe cache de entorno entre hooks: cada hook corre en su propio subproceso, asi que un os.environ escrito por uno nunca es visible para otro (Opus review P2-5, 2026-08-13, elimino el intento previo de cache via DQIII8_PROJECT).
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 · 50 lines · 32 tokens per session scan A a0d39e42d610

Subscribe to this mod's changes

proyecto is a command published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 503 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 2026-08-30.