BC openclaw-elontools-optimizer-v3
Otimizações SEGURAS para OpenClaw — apenas configurações que economizam tokens sem NENHUM risco de perda de contexto ou loops infinitos. QUANDO USAR: - Setup inicial de nova instância OpenClaw - Reduzir custo de heartbeats (usa modelo barato) - Desabilitar plugins/canais não usados - Limpar sessões antigas automaticamente O QUE FAZ (4 otimizações seguras): 1. Heartbeat Econômico — usa Haiku para heartbeats (não gasta Opus/Sonnet) 2. Plugin Cleanup — desabilita plugins de canais não configurados 3. Sub-agent Auto-Archive — limpa sessões de sub-agentes após 30min 4. Session Cleanup — remove sessões inativas após 7 dias O QUE NÃO FAZ (PROIBIDO — causa loops): ❌ NÃO mexe em contextPruning (NUNCA!) ❌ NÃO mexe em compaction (NUNCA!) ❌ NÃO mexe em bootstrapMaxChars (NUNCA!) ❌ NÃO mexe em softTrim/hardClear (NUNCA!) ❌ NÃO altera web_fetch maxChars ❌ NÃO altera reserveTokensFloor ou maxHistoryShare LIÇÃO APRENDIDA (2026-03-26): A v1/v2 desta skill causou loop infinito de tool_calls em produção. Rublo consumiu 44.6M input tokens em 1 dia (1398 requests) por causa de contextPruning agressivo + bootstrapMaxChars que cortava instruções. NUNCA MAIS mexer nessas configs.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1175 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 489 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1174: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.