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/checkgit 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 | $0.00030 | $0.00760 |
| Opus 5 | $0.00015 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
check 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:check
Verificação ad-hoc de duplicidade para uma feature antes de plan.
Argumentos
$ARGUMENTS - descrição da feature em texto livre. Exemplos:
- "endpoint de export CSV de pedidos"
- "autenticação via JWT"
- "rate limiting no gateway"
Workflow
Passo 1 - Pre-flight
Verificar .first-plan/ existe.
Passo 2 - Match contra matriz existente
Aplicar algoritmo da skill reconciliation:
- Extrair termos-chave da descrição
- Match contra entries em
09-features/INDEX.mdpor overlap de termos
Se match encontrado: mostrar feature existente + status:
Match encontrado: F5 - "Two-Factor Authentication" (status: IN_PROGRESS)
Detalhes:
- Fonte: JIRA-789
- Confidence: 0.78
- Evidência: branch feat/2fa, PR #42 aberto há 3 dias
- Última atualização: 2026-04-30
Recomendação:
- Esta feature está em progresso. Considerar continuar nesse PR em vez de começar do zero.
- Para ver detalhes: cat .first-plan/09-features/two-factor-authentication.md
- Para colaborar: gh pr checkout 42
Passo 3 - Sem match na matriz - busca direta
Se não match na matriz (pode ser feature nova ou matrix stale):
Spawnar reconciliation-auditor com feature_query=<descrição>:
Task(
subagent_type="reconciliation-auditor",
description="Ad-hoc feature check",
prompt="Audit single feature: '<argumento>'. Apply full classification algorithm against current codebase. Return status + evidence."
)
Passo 4 - Reportar resultado
Caso 1 - feature realmente nova:
"<descrição>" parece ser feature nova - sem evidência de implementação ou spec.
Status sugerido se planejar: NOT_STARTED
Próximo passo: /fp:plan "<descrição>"
Caso 2 - feature existente que não estava na matriz (matrix stale):
Encontrei evidência da feature mas não estava em 09-features/.
Evidência:
- internal/handler/export.go:45 (handler já existe)
- internal/handler/export_test.go (com tests)
Status inferido: IMPLEMENTED (confidence 0.78)
Sugestão:
- Não duplicar - feature parece já existir
- Atualize a matriz: /fp:refresh 09-features
- Se quer modificar a feature existente, especifique melhor o que deseja
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 · 107 lines · 30 tokens per session scan A 032578368ad6
check is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 760 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.