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.
npx agentmods add commands/vynazevedo/first-plan/whygit clone --depth 1 https://github.com/vynazevedo/first-planWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.00778 |
| Opus 5 | $0.00017 | $0.00389 |
| Sonnet 5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
why 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:why
Query da camada compilada: contexto sobre algo do projeto.
Argumentos
$ARGUMENTS - alvo da consulta. Pode ser:
- Path de arquivo:
.first-plan:why src/auth/jwt.go - Símbolo:
/fp:why ValidateEmail - Padrão:
/fp:why "wrapping de erros" - Decisão:
/fp:why "uso de Bull em vez de BullMQ"
Workflow
Passo 1 - Classificar o argumento
- Path de arquivo (existe no filesystem) -> consulta sobre arquivo
- Símbolo (CamelCase, snake_case identificável) -> consulta sobre símbolo
- Frase entre aspas ou texto livre -> consulta livre
Passo 2 - Buscar evidência na camada
Para path:
- Em
01-topology/architecture.md- role do arquivo - Em
02-conventions/*- exemplos referenciando este path - Em
03-reuse/*- se está catalogado como reusável - Em
05-risks/*- se está em alguma lista de risco - Em
06-rationale/why.md- decisões inferidas - Em
01-topology/ownership.md- dono inferido - Em
01-topology/activity.md- hot zone? frozen? - Git:
git log --follow <path>para histórico
Para símbolo:
- Grep em
03-reuse/*.md- ja catalogado? - Grep no projeto: definição + usos
- Em
02-conventions/*- exemplo de algum padrão? - Em
06-rationale/do.mdoudont.md- é um padrão?
Para padrão:
- Grep em
02-conventions/*- existe regra? - Grep em
06-rationale/*- existe rationale? - Grep em
08-meta/questions.md- é uma pergunta aberta?
Para decisão:
- Em
06-rationale/why.md - Git log com mensagens relacionadas
- ADRs em
docs/adr/se existirem
Passo 3 - Sintetizar resposta
Estrutura:
sobre: <argumento>
Resumo:
<1-3 linhas direto ao ponto>
Contexto detalhado:
- Localização: <path:line se aplicável>
- Papel no projeto: <inferido de architecture.md>
- Padrões aplicáveis: <linkar conventions>
- Quem domina: <de ownership.md>
- Histórico relevante: <commits/PRs relacionados>
- Decisões inferidas: <de why.md>
Riscos / cuidados:
<de risks/*.md se aplicável>
Como reusar / chamar:
<de reuse/INDEX.md se aplicável>
Confidence: <baseado nos findings>
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.
- yesterday First seen · 98 lines · 35 tokens per session scan A 7116784a8736
why is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 778 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.
Other commands, from other repositories
gate
Run the full local gate (fmt, lint, test, build, docs, and fuzz when a parser changed) and report only what failed.
release
Prepare the next release per RELEASING.md — gate, price table, surface audit, changelog — and stop at the tag command.
matcha:why
🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.
pr-review
Review a PR across multiple dimensions (description, code, scan, tests).
setup
Generate HOTL adapter files for your team's code assistants (Codex, Cline, Cursor, Copilot).
subagent-execute
Execute a reviewed HOTL workflow in this session with delegated subagent steps and controller-owned verification.