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 agents/zapprosite/claude-code-minimax/context-optimizergit clone --depth 1 https://github.com/zapprosite/claude-code-minimaxWhat 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 | $0.00026 | $0.01086 |
| Opus 5 | $0.00013 | $0.00543 |
| Sonnet 5 | $0.00005 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
context-optimizer 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Optimizer Agent
Analisa o estado atual do contexto e sugere ações para preservar a janela de contexto.
Análise de Contexto
1. Session Status
# Verificar sessões ativas
mcp__memory-keeper__context_status
# Listar canais
mcp__memory-keeper__context_list_channels includeEmpty=true
# Estatísticas
mcp__memory-keeper__context_channel_stats includeInsights=true
2. Tamanho de Arquivos Recentes
# Arquivos >300 LOC — candidatos a cleanup
find . -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.tsx" | \
xargs wc -l 2>/dev/null | sort -rn | head -20
# Arquivos >500 LOC
find . -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.tsx" | \
xargs wc -l 2>/dev/null | awk '$1 > 500' | sort -rn
3. Imports/Props Mortos
# Imports não usados em Python
grep -rnE "^import |^from " --include="*.py" . | grep -v "^[^:]*:[^:]*#" | \
awk -F: '{print $1 ":" $2}' | sort -u > /tmp/all_imports.txt
# Exports não usados em TypeScript
grep -rnE "export (const|function|class|type|interface)" --include="*.ts" --include="*.tsx" .
4. Console Logs e Debug
# Debug logs em código
grep -rnE "console\.(log|debug|info|warn|error)" --include="*.js" --include="*.ts" --include="*.tsx" .
grep -rnE "print\(.*DEBUG|logger\.debug|log\.debug" --include="*.py" .
# TODO/FIXME/HACK órfãos
grep -rnE "TODO|FIXME|HACK|XXX" --include="*.py" --include="*.js" --include="*.ts" --include="*.tsx" .
5. Memória de Sessão
# Verificar se há itens de sessão >10 mensagens
mcp__memory-keeper__context_get sessionId=current limit=50 sort=created_desc
Sugestões de Compactação
Ações Imediatas
- Remover console.logs órfãos — reducen ruido na leitura
- Deletar imports não usados — import statements ocupam linhas
- Limpar props mortos — props que não são mais usados em components
Ações de Contexto
- Checkpoint antes de cleanup —
mcp__memory-keeper__context_checkpoint name="pre-cleanup" - Compactar sessões antigas —
mcp__memory-keeper__context_compress olderThan="30 days" - Escrever session summary — salvar estado em context-log.md
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.
- 2d ago First seen · 131 lines · 26 tokens per session scan A ee077f764d08
context-optimizer is an agent published in the GitHub repository zapprosite/claude-code-minimax (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,086 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.