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/plangit 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 | $0.00047 | $0.01694 |
| Opus 5 | $0.00023 | $0.00847 |
| Sonnet 5 | $0.00009 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
plan 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:plan
Gera plano da Fase 2 - sempre pausa pedindo aprovação humana.
Argumentos
$ARGUMENTS - descrição da feature solicitada em texto livre. Exemplos:
- "adicionar endpoint de export CSV para /orders"
- "implementar autenticação por API key além do JWT existente"
- "adicionar rate limiting por IP no gateway"
Workflow
Passo 1 - Pre-flight
- Verificar
.first-plan/existe eSTATE.mdindica fase >=discovered - Verificar se já há plano ativo (
07-state/STATE.mdemawaiting_approvalouexecuting):- Se sim, perguntar: "Plano está . Substituir? (sim/não)"
- Não prosseguir sem confirmação
- Verificar staleness: se muitos arquivos stale, recomendar
/fp:refreshantes
Passo 2 - Verificação de duplicidade
Aplicar skill reconciliation:
- Spawnar
reconciliation-auditorcomfeature_query=<argumento>:
Task(
subagent_type="reconciliation-auditor",
description="Duplicate check for plan request",
prompt="Audit feature: '<arg>'. Apply classification. Return status + evidence + recommendation."
)
-
Se status = IMPLEMENTED:
- PARAR - perguntar ao usuário:
Esta feature parece já implementada (<evidência>). Opções: A) Cancelar plano (a feature já existe) B) Modificar a feature existente em vez de criar nova C) Seguir com plano mesmo assim (pode estar errado a matriz) Qual? [A/B/C] - Não prosseguir sem decisão.
- PARAR - perguntar ao usuário:
-
Se status = IN_PROGRESS:
- Avisar: "Há trabalho em flight em /. Sugiro continuar nesse contexto em vez de plano novo."
- Perguntar se quer prosseguir mesmo assim.
-
Se status = DRIFTED:
- Perguntar: "A feature solicitada é justamente reconciliar o drift detectado em ?"
-
Se status = SPEC_ONLY ou NOT_STARTED ou nova: Prosseguir.
Passo 3 - Coleta de contexto relevante
Ler trechos relevantes da camada compilada:
01-topology/architecture.md- onde a feature se encaixa01-topology/boundaries.md- se feature toca contratos02-conventions/*- todas as convenções aplicáveis03-reuse/INDEX.md- candidatos a reuse04-domain/*- entidades e flows relevantes05-risks/*- riscos em paths que provavelmente serão tocados06-rationale/*- decisões a respeitar07-state/in-flight.md- PRs/branches que podem conflitar08-meta/questions.md- perguntas abertas relevantes
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.
- 3d ago First seen · 190 lines · 47 tokens per session scan A 00756e694d68
plan is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 1,694 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:review
🍵 Review gate — risk-based code review (L0-L3). Nothing ships until this passes.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
matcha:why
🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.
setup
Generate HOTL adapter files for your team's code assistants (Codex, Cline, Cursor, Copilot).