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/hmaurus/masterclaude/pdir-deploygit clone --depth 1 https://github.com/hmaurus/masterclaudeWhat 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 | $0.00032 | $0.00426 |
| Opus 5 | $0.00016 | $0.00213 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
pdir-deploy 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.
What it actually says
PDIR: Deploy
Faz deploy para produção via merge para a branch de produção.
Em qualquer passo, se algo falhar ou faltar informação, informe o erro e pergunte ao usuário como prosseguir.
Instruções
1. Identificar Fluxo de Deploy
Ler CLAUDE.md do projeto para identificar:
- Branch de trabalho (ex:
develop) - Branch de produção (ex:
main) - Método de deploy (CI/CD automático em push, manual via
gh workflow run, etc.)
Se não houver documentação de deploy, perguntar ao usuário.
2. Verificar Estado
git status -sb
git branch --show-current
- Se houver mudanças pendentes: informar e perguntar se deve commitar antes
- Se não estiver na branch de trabalho: informar e perguntar como prosseguir
3. Sincronizar
git pull --ff-only
4. Merge para Produção
git checkout [branch-producao]
git merge [branch-trabalho] --no-edit
git push origin [branch-producao]
5. Voltar para Branch de Trabalho
git checkout [branch-trabalho]
6. Verificar Deploy (se CI/CD)
Se o projeto usa CI/CD automático, verificar o status do workflow:
gh run list --limit 1 --json status,conclusion,databaseId
Se o deploy falhar, informar o erro ao usuário.
7. Feedback Final
Deploy iniciado!
Merge: [branch-trabalho] → [branch-producao]
Branch atual: [branch-trabalho]
Deploy: [método — ex: CI/CD automático, gh workflow run, etc.]
Próximos passos:
- commit (continuar trabalhando)
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 · 74 lines · 32 tokens per session scan A 27524d48db39
pdir-deploy is a command published in the GitHub repository hmaurus/masterclaude (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 426 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.