# Sapheneia

> Shape the agent's own replies for AuDHD readers with explicit actions, boundaries, state, evidence and next steps, and shape every piece of prose the agent writes down, including an agent-authored audit record, a GitHub issue title and body, a GitHub issue comment, a pull request, a repository document and a commit message, to the shortest form that keeps its protected evidence intact. Session shaping persists until the user turns it off; the bounded durable-record operation does not activate session mode.

## Facts
- Page: https://tashan.sh/capability/skill-wildcat-finance-sapheneia
- tashan id: skill:wildcat-finance/sapheneia
- Source: https://github.com/wildcat-finance/skills
- Type: skill
- Category: productivity
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 100.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r sapheneia ~/.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 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.