jar-reis/hermes-skills/caliber

CALIBER

CALIBER is a model-routing skill. It turns a request into a task-surface demand vector, compares that vector against a model capability matrix, and returns the cheapest constructor that can clear the task with the right defender.

A constructor is:

model + deployment path + context + retrieval + tools + verifier + human gate

Core rule

Do not ask “what is the best model?” Ask:

What is the cheapest allowed constructor whose proven capabilities clear this

task's required surfaces and whose defender can verify the result?

Demand levels

Workflow

1. Gate the deployment pool: regulated/private data, local-only requirements,

secrets, production writes, or external sends may restrict allowed models.

1. Break the task into surfaces such as reasoning, coding, long context, tool use,

media, structured output, local/private, or compliance.

1. Assign required level per surface.
2. Filter candidate models/deployments from references/model-capability-matrix.yaml.
3. Attach defenders from references/defender-registry.md.
4. Pick the cheapest viable constructor.
5. If the defender fails, escalate one tier or switch specialist lane.

Output shape

Task surfaces:
- <surface>: required level <n> — <why>
 
Gate pool:
- allowed deployments:
- excluded deployments:
 
Candidate comparison:
- cheapest viable:
- strongest reliable:
- local/private option:
- specialist option:
 
Defenders:
- required verifier(s):
- human gate:
 
Recommendation:
- primary constructor:
- fallback constructor:
- escalation rule:
- evidence confidence:

References

• references/surface-taxonomy.md
• references/model-capability-matrix.yaml
• references/model-capability-schema.json
• references/benchmark-source-ledger.md
• references/defender-registry.md
• references/routing-policy-v0.3.md
• references/model-registry.md
• references/demand-card.md