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/ownergit clone --depth 1 https://github.com/vynazevedo/first-planWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/vynazevedo/first-plan/owner)<a href="https://agentmods.dev/commands/vynazevedo/first-plan/owner"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/owner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.00587 |
| Opus 5 | $0.00015 | $0.00293 |
| Sonnet 5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
owner 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 4d 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.
What it actually says
/fp:owner
Ownership inferido por path.
Argumentos
$ARGUMENTS - path de arquivo ou pasta.
Workflow
Passo 1 - Pre-flight
Verificar git repo + .first-plan/01-topology/ownership.md.
Passo 2 - Match
Procurar $ARGUMENTS em ownership.md:
- Match exato de path
- Match de prefixo (e.g., consultar
internal/auth/jwt.goquandoownership.mdlistainternal/auth/)
Se nao encontrar match, rerun inline:
git shortlog -sne -- <path> | head -10
Passo 3 - Apresentar
Ownership de <path>
Top contributor: João Silva <[email protected]>
- 47% das alterações (28 commits, 1234 linhas modificadas)
- Última contribuição: ha 3 dias
Co-autores notáveis (>= 20%):
- Maria Lima - 31% (18 commits)
- Pedro Souza - 22% (12 commits)
Outros contribuintes:
- 5 pessoas com < 10% cada
Atividade temporal:
- Última modificação: <data> (<X dias atrás>)
- Modificações nos últimos 30 dias: <N>
- Modificações nos últimos 90 dias: <M>
Implicações:
- Antes de mudança grande, considerar perguntar ao top contributor
- Alta dispersão = conhecimento difuso, possivelmente padrões inconsistentes
- Última modificação > 1 ano + contribuidor original inativo = candidato a dead code
Passo 4 - Casos especiais
Sem ownership claro (todos < 30%):
<path> não tem owner claro - 12 pessoas contribuíram, top com apenas 18%.
Implicação: padrões podem estar inconsistentes. Olhar commits recentes mais que histórico geral.
Path órfão (top contributor inativo):
<path> é potencialmente órfão.
Top contributor (João Silva) não fez commits há 8 meses.
Considerar:
- Validar se este código ainda é usado (via co-change graph: /fp:cochange <path>)
- Procurar outro mantenedor antes de mexer
Cuidados
- Comparar com
01-topology/ownership.mdem vez de sempre rodar git pode dar resultado mais rápido mas menos atualizado. - Se a camada está stale, oferecer refresh inline.
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.
- 4d ago First seen · 82 lines · 29 tokens per session scan A 0cfefed31bc2
owner is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 587 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.
Other commands, from other repositories
set-tracker
Set the issue tracker for the current project.
maggy-init
Interactive wizard that configures Maggy for the user's org, issue tracker, and codebases. Writes /.maggy/config.yaml and ensures deps are installed.
resume-project
Cold-start project — BOARD, PROGRESS, stalled tasks, worktrees.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.