compute-ladder
The compute-ladder skill defines a four-tier model fallback strategy for routing AI requests based on infrastructure availability and cost constraints. It specifies primary models (local Ollama instances), fast free cloud alternatives (Cerebras), standard free cloud options (OpenRouter), deep reasoning models, and restricted paid Claude Opus for audits only, with automatic fallback triggers for rate limiting and timeouts while preventing quality-based preference switching. Health checks and cost guardrails monitor Tier 0 local availability, Tier 1 Cerebras API access, and OpenRouter spending thresholds to flag excessive Tier 4 usage.
git clone --depth 1 https://github.com/open-gitagent/opengap /tmp/compute-ladder && cp -r /tmp/compute-ladder/examples/jason-my-claw-is-the-law-deebee-4567b4/skills/compute-ladder ~/.claude/skills/compute-ladderSKILL.md
# Compute Ladder
## Tier Definitions
```
Tier 0 — Local (never dies, zero cost)
ollama/qwen3-coder:latest primary, MoE, 128 TPS, 64k ctx
ollama/gpt-oss:20b fallback, 32k ctx HARD LIMIT
Tier 1 — Fast Free Cloud (up to 2100 TPS)
cerebras/qwen-3-235b-a22b-instruct-2507 235B MoE, fast free
cerebras/llama3.1-8b 8B, ultra-fast light tasks
Tier 2 — Free Cloud (normal latency)
openrouter/z-ai/glm-4.5-air
openrouter/qwen/qwen3-coder
Tier 3 — Free Cloud Deep Reasoning
openrouter/nousresearch/hermes-3-llama-3.1-405b:free
Tier 4 — Break-Glass (paid, restricted use)
openrouter/anthropic/claude-opus-4.6 [narco-check and audit ONLY]
```
## Fallback Rules
**DO fallback when:**
- HTTP 429 (rate limited)
- Connection timeout (> 90s)
- Stream death / incomplete response
**DO NOT fallback when:**
- Task seems "complex" or "important"
- You want "better" output quality
- Previous attempt gave a poor answer
Use the primary model. Iterate. Fallback is for infrastructure failure, not preference.
## Health Check
```bash
# Tier 0
curl -s localhost:11434/api/tags | python3 -c "import json,sys; d=json.load(sys.stdin); print('TIER-0 OK:', len(d['models']), 'models')"
# Tier 1
curl -s -o /dev/null -w "%{http_code}" \
-H "Authorization: Bearer $CEREBRAS_API_KEY" \
https://api.cerebras.ai/v1/models
# Tier 4
curl -s -o /dev/null -w "%{http_code}" \
https://openrouter.ai/api/v1/models
```
## Cost Guard
```bash
# Check today's OpenRouter spend
curl -s "https://openrouter.ai/api/v1/auth/key" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
| python3 -c "
import json,sys
d=json.load(sys.stdin)['data']
print(f'today: \${d[\"usage_daily\"]:.2f} | week: \${d[\"usage_weekly\"]:.2f} | month: \${d[\"usage_monthly\"]:.2f}')
"
```
Daily > $5: flag to Ludo.
Weekly > $50: flag immediately — tier-4 model is likely being over-used.Reviews financial documents (prospectuses, ADVs, marketing materials) for FINRA 2210 compliance, required disclosures, and balanced presentation. Use when reviewing financial statements, audit documents, regulatory filings, or when the user mentions compliance checks, financial audits, or document verification.
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.
Converts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models formats, and imports from Claude, Cursor, and CrewAI projects. Use when the user wants to convert an agent, migrate to another framework, export to LangChain/AutoGen/CrewAI, or import from existing automation tools.
Guides installation of gitagent and creation of first agent with scaffolding, configuration, and validation. Use when the user is new to gitagent, asks how to get started, wants to install gitagent, set up their first agent, or says 'how do I start?'
Searches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages the skill lifecycle. Use when the user wants to find skills, add new capabilities, install a skill, browse available skills, create a custom skill, or manage the skills system.
Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.
>