agentmods.dev

self-improve

self-improve is a command for Claude Code from pedrol-cmd/brain-drin. It costs 23 tokens per session (644 once invoked), scanned A, original, MIT.

A process for improving an agent setup by keeping changes supported by repeated evidence and removing changes that do not help.

In plain words
What is it for?
Use it to review recent session notes, knowledge files, the CLAUDE.md instructions, agents, and commands, then remove, rewrite, or consolidate weak guidance.
Why use it?
It reduces bloated or ineffective instructions by separating recurring signals from one-off events and corrected mistakes.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

not rated 12repo +1 7mo ago A scan 23 tokens original MIT

Good fit Use it to review recent session notes, knowledge files, the CLAUDE.md instructions, agents, and commands, then remove, rewrite, or consolidate weak guidance.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/pedrol-cmd/brain-drin/self-improve
View source ↗ pedrol-cmd/brain-drin
Install

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.

Clone the repo
git clone --depth 1 https://github.com/pedrol-cmd/brain-drin

Made for: Claude Code.

Wrote 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.

agentmods badge for self-improve

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedrol-cmd/brain-drin/self-improve/github.svg)](https://agentmods.dev/commands/pedrol-cmd/brain-drin/self-improve)
Your own site
<a href="https://agentmods.dev/commands/pedrol-cmd/brain-drin/self-improve"><img src="https://agentmods.dev/badge/commands/pedrol-cmd/brain-drin/self-improve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for self-improve

Your own site · 80×15
<a href="https://agentmods.dev/commands/pedrol-cmd/brain-drin/self-improve"><img src="https://agentmods.dev/badge/commands/pedrol-cmd/brain-drin/self-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00644
Opus 5.5 $0.00009 $0.00258
Sonnet 5.5 $0.00005 $0.00129
Haiku 4.5 $0.00002 $0.00064

Measured 2mo ago against content hash a4226fbb4fa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

self-improve 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 2mo 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.

.claude/commands/self-improve.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/self-improve

Princípio

Sistema que aprende tudo fica gordo. A regra é: só entra o que prova valor. Tudo que não prova, sai.

Resultado esperado: CLAUDE.md e agentes menores e mais precisos a cada ciclo, não maiores.

Coleta de evidências

Ler .drin/memory-compiler/daily/ (últimas 2 semanas) e .drin/memory-compiler/knowledge/.

Separar em dois grupos:

SINAL (vale aprender):

  • Padrão apareceu 3+ vezes nas sessões
  • Pedro disse "exatamente isso", "perfeito", "assim sempre" — validação explícita
  • Abordagem resolveu problema que antes travava
  • Pedro repetiu o mesmo pedido de formas diferentes — indica lacuna no sistema

RUÍDO (ignorar):

  • Aconteceu 1 vez, contexto específico
  • Pedro corrigiu depois — aprender o erro seria pior
  • Pedro pediu para cortar, simplificar, parar de fazer algo
  • Específico do projeto atual, não universal

Análise do sistema atual

Para cada item no CLAUDE.md, agentes e comandos, verificar:

Pergunta Se não →
Isso foi usado nas últimas 2 semanas? Candidato a remoção
Isso está gerando o comportamento certo? Candidato a reformulação
Isso está duplicado em outro lugar? Consolidar ou remover
Isso está fazendo o sistema maior sem torná-lo melhor? Remover

Propostas — formato obrigatório

Cada proposta deve ter:

TIPO: ADICIONAR / REMOVER / REFORMULAR
ONDE: [arquivo exato, linha se aplicável]
O QUE: [mudança específica]
EVIDÊNCIA: [observado X vezes em [datas] / validado explicitamente em [data]]
IMPACTO ESPERADO: [por que isso torna o sistema melhor]

Nenhuma proposta sem evidência. "Acho que seria melhor" não é evidência.

Regras de qualidade

  1. Redução > Adição. Se o ciclo não removeu nada, o sistema provavelmente só inchou.
  2. CLAUDE.md máximo 80 linhas. Se ultrapassar, algo menos valioso precisa sair.
  3. Agente novo só entra se substituir comportamento manual recorrente — não por "pode ser útil".
  4. Comando novo só entra se Pedro usaria pelo menos 1x/semana.
  5. Toda adição tem data de revisão — se em 30 dias não foi usado, remove automaticamente.

Read the full file on GitHub · 78 lines

Changes

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.

  1. 2mo ago First seen · 78 lines · 23 tokens per session scan A a4226fbb4fa4

Subscribe to this mod's changes

self-improve is a command published in the GitHub repository pedrol-cmd/brain-drin (12 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 644 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Building agents
Related

self-improve compared with commands from other repositories

self-improve next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
self-improvepedrol-cmd/brain-drinCommand127mo agoMITA23Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code