// Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty.
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.
Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nightly deep dive. Uses Opus 4.6 as the auditor model.
| name | compute-ladder |
| version | 1.0.0 |
| description | Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty. |
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]
DO fallback when:
DO NOT fallback when:
Use the primary model. Iterate. Fallback is for infrastructure failure, not preference.
# 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
# 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.