# Codi Agents

> Whale-spawns-Codi-Agents orchestration dispatcher. Routes T0-T2 orchestration tasks (prompt sharpening, persona detection, calibration scanning, hallucination pre-flight, lightweight jury) AWAY from the active premium model (whale = Sonnet/Opus/Claude) and TO cheap Codi Agents (Gemini Flash via OAuth, GPT-5.4 via codex CLI). Fixes the token-burn bug where premium reasoning capacity was being spent on mechanical orchestration. FAIL-HARD: if no Codi Agents are reachable, BLOCKS — never silently falls back to whale. Activate when the user says "codi agents", "spawn agents", "delegate to agents", "stop burning tokens", "cheap orchestration", or when any other skill needs a T0-T2 verdict on prompt-sharpen / persona-detect / calibration-scan / hallucination-preflight / t0t2-jury.

## Facts
- Page: https://tashan.sh/capability/skill-thewhyman-codi-agents
- tashan id: skill:thewhyman/codi-agents
- Source: https://github.com/thewhyman/prompt-engineering-in-action
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 94.0
- Freshness: 88.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: AGPL-3.0
- Official: no

## Install

```sh
cp -r codi-agents ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-09 by tashan (https://tashan.sh) from public evidence. Scorer s5.