Skip to Content
DocsGuidesAgent Matrix & Recommender

The agent matrix is a read-only capability view that joins the curated agent registry with your local usage statistics. It powers the recommendation badges you see when starting a feature while maintainer-owned tooling keeps pricing, scores, notes, and quarantine state current.

What the matrix contains

For every (agent, model) pair registered in templates/agents/<id>.json, the matrix tracks:

FieldSourceDescription
pricingRegistryPublic API cost in $/M tokens (inputPerM, outputPerM)
notes.<op>RegistryHuman-readable capability note for each operation
score.<op>RegistryQualitative score 1–5 for each operation
lastRefreshAtRegistryWhen this entry was last refreshed by maintainer tooling
statsLocal telemetryFeatures run, total cost, sessions for this model

The four operations are: draft, spec_review, implement, review. Scores and notes can differ per operation — a model that excels at implementation may score lower for spec writing.

Recommendation badges in the start modal

When you open the start modal for a feature, Aigon calls /api/recommendation/:type/:id to rank available agents for the relevant operation. The top candidates are shown alongside the agent/model dropdowns:

  • ✨ Best value — highest score-to-cost ratio
  • ⚡ Fastest — lowest latency / cost for this operation
  • 🎯 Highest quality — highest qualitative score for this operation

Badges are suggestions only. The user still picks the agent and model — the recommender never overrides your choice.

Cells with no benchmark data (zero sessions) fall back to qualitative score alone and show confidence: low in the ranking rationale. The recommender never invents numbers to fill empty cells.

How ranking works

The score for each (agent, model, operation) triplet is:

score = qualitative_score (1–5) − cost_penalty (normalised $/op)

qualitative_score comes from score.<op> in the agent registry. cost_penalty is derived from actual session cost in your local telemetry (stats-aggregate.perTriplet). Quarantined models are excluded from ranking by default.

Keeping the matrix current

OSS Aigon ships curated registry data in templates/agents/*.json and exposes it through Settings, model pickers, and recommendation APIs. Benchmark sweeps, model discovery, registry refresh, and direct registry mutation are maintainer-owned workflows outside the OSS user CLI.

Agent registry fields reference

In templates/agents/<id>.json, each entry in cli.modelOptions[] can carry:

{ "value": "claude-opus-4-7", "label": "Opus 4.7", "pricing": { "inputPerM": 15.0, "outputPerM": 75.0 }, "notes": { "implement": "Strong on multi-file reasoning and architecture decisions.", "review": "Thorough but slow — best for high-stakes reviews." }, "score": { "draft": 4, "spec_review": 5, "implement": 5, "review": 5 }, "lastRefreshAt": "2026-04-20T10:00:00.000Z" }

Models with quality or safety issues can be marked quarantined rather than deleted:

{ "value": "some-model", "quarantined": { "reason": "Hallucinated test output in F358", "since": "2026-03-15" } }

Quarantined models are excluded from recommendations and shown with a warning in the Settings tab matrix view.

Last updated on