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/initgit 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 | $0.00049 | $0.01792 |
| Opus 5 | $0.00024 | $0.00896 |
| Sonnet 5 | $0.00010 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
init 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:init
Compilação completa do contexto do projeto-alvo.
Argumentos
$ARGUMENTS - opcionalmente --force para reconstruir do zero ignorando cache.
Workflow
Passo 1 - Pre-flight check
- Verificar diretório atual é um projeto (tem manifesto, código, etc) - não rodar em $HOME ou diretório vazio
- Verificar se ja existe
.first-plan/:- Se existe E não tem
--force: avisar usuário e oferecer/fp:refreshem vez - Se existe E tem
--force: backup em.first-plan/.backup-<timestamp>/antes de prosseguir
- Se existe E não tem
- Verificar git repo. Se sim, ativa Git Intelligence; se não, marcar seções correlatas como N/A.
Passo 2 - Bootstrapping
Criar a estrutura .first-plan/ copiando templates do plugin:
mkdir -p .first-plan/{00-mission,01-topology,02-conventions,03-reuse,04-domain,05-risks,06-rationale,07-state/{plans,reports,sessions},08-meta,09-features}
Copiar templates de ${CLAUDE_PLUGIN_ROOT}/templates/ para .first-plan/ no projeto-alvo. Não copiar ${CLAUDE_PLUGIN_ROOT}/meta-templates/ - esses sao internos do plugin (usados por /fp:plan e /fp:execute para gerar plans/reports/features individuais; nao devem ir pro .first-plan/ do projeto). Substituir placeholders básicos:
PLACEHOLDER_TIMESTAMP-> ISO 8601 atualPLACEHOLDER_ROOT-> caminho absoluto do projetoPLACEHOLDER_NAME-> nome do projeto (de package.json/go.mod/etc, ou nome da pasta)PLACEHOLDER_PHASE->discovering
Adicionar ao .gitignore do projeto se não estiver:
.first-plan/cache/
.first-plan/07-state/sessions/
.first-plan/.backup-*/
Passo 3 - Discovery (subagent)
Spawnar discovery-analyst via Task tool:
Task(
subagent_type="discovery-analyst",
description="Phase 1 Discovery for first-plan",
prompt="<contrato detalhado com project_root, lens_skills_available, time_budget_minutes=8>"
)
Receber findings estruturados.
Passo 4 - Pattern Extraction (subagent)
Spawnar pattern-archeologist em paralelo (mesma mensagem, múltiplas Task tool calls):
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 · 204 lines · 49 tokens per session scan A f12ce6d55f45
init is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,792 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.