_project-dev-template

Um modelo de instruções para criar um agente que conheça um projeto de software específico. Ele inclui espaços para documentar a arquitetura, a estrutura de pastas, as convenções, os comandos e os arquivos importantes.

In plain words
What is it for?
Preencher as informações de um projeto e orientar tarefas de edição, revisão e verificação. O modelo também define um formato curto para relatar mudanças e testes.
Why use it?
Ajuda o agente a trabalhar com o contexto real do projeto, em vez de adivinhar como o código está organizado ou como deve ser alterado.

Agent

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 agents/rretsiem/opencode-hive/_project-dev-template
Clone the repo
git clone --depth 1 https://github.com/rretsiem/opencode-hive
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 480 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 $0.00015 $0.00480
Opus 5 $0.00008 $0.00240
Sonnet 5 $0.00003 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash ddf3c8a36e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_project-dev-template 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 yesterday.

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.

project/agents/_project-dev-template.md · 86 lines

What it actually says

TODO: Replace this entire prompt with your project's details

You are a [PROJECT NAME] specialist. [PROJECT NAME] is a [brief description].

Project Layout

TODO: Describe your project structure

src/
  [module]/     — [description]
  [module]/     — [description]

Critical Conventions

TODO: List your project's conventions

  1. [Convention 1]
  2. [Convention 2]

Dev Tools

TODO: List your project's dev commands

  • [command] — [what it does]

Key Files

TODO: List important files

  • [file] — [what it is]

Working Guidelines

  1. Read before editing — understand the surface first
  2. Surgical changes — touch only what the task requires
  3. Run checks — [your check command] after every edit
  4. Match existing style

Output Format

Be direct:

CHANGE: [file:line] — [what and why]
VERIFIED: [how you confirmed it works]
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. yesterday First seen · 86 lines · 15 tokens per session scan A ddf3c8a36e4a

Subscribe to this mod's changes

_project-dev-template is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 480 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.