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.
git clone --depth 1 https://github.com/adrianosantostreina/delphi-devWrote 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/adrianosantostreina/delphi-dev/contribute-kb)<a href="https://agentmods.dev/commands/adrianosantostreina/delphi-dev/contribute-kb"><img src="https://agentmods.dev/badge/commands/adrianosantostreina/delphi-dev/contribute-kb.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 5.1 | $0.00065 | $0.00676 |
| Opus 5 | $0.00032 | $0.00338 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
contribute-kb 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idioma de saída
Detecte o idioma da primeira mensagem do usuário. Padrão: pt-BR. Honor: "respond in English" → en-US.
O que este comando faz
Coleta os arquivos de knowledge/local/ gerados pelos hooks nas últimas sessões,
sanitiza dados sensíveis e abre um Pull Request no repositório GitHub do plugin
para que o autor possa revisar e mesclar o conhecimento com a base comunitária.
Fluxo
pt-BR
-
Verificar se há arquivos em
knowledge/local/nos últimos 30 dias- Se vazio: informar que não há aprendizados para contribuir e sugerir usar o plugin em mais sessões Delphi
- Se houver arquivos: listar os arquivos encontrados com data e número de chunks
-
Mostrar preview dos primeiros 3 chunks de cada arquivo e perguntar: "Quer contribuir estes X aprendizados para a base de conhecimento comunitária? (s/n)"
-
Se confirmado:
- Sanitizar: remover paths absolutos do usuário, substituir por
~/... - Remover qualquer nome de empresa, CPF, CNPJ, IP de produção (regex)
- Copiar arquivos sanitizados para
knowledge/community/YYYY-MM-DD-contrib-{hash}.md - Commitar a mudança
- Abrir PR via
gh pr create:Título: kb: add community learnings ({N} chunks, {date}) Body: Contribuição automática via /contribute-kb. Revisar antes de mesclar.
- Sanitizar: remover paths absolutos do usuário, substituir por
-
Exibir URL do PR criado
-
Edge case —
knowledge/local/vazio: pt-BR: "Não encontrei aprendizados recentes para contribuir. Continue usando o plugin em sessões Delphi — os hooks capturam automaticamente o que você aprende." en-US: "No recent learnings found to contribute. Keep using the plugin in Delphi sessions — hooks automatically capture what you learn."
en-US
-
Check for files in
knowledge/local/from the last 30 days- If empty: inform user and suggest more Delphi sessions
- If files exist: list them with date and chunk count
-
Show preview of first 3 chunks per file and ask: "Contribute these X learnings to the community knowledge base? (y/n)"
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.
- 8d ago First seen · 68 lines · 65 tokens per session scan A a5c91d57341a
contribute-kb is a command published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 676 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.