Tellonce — Development skill for Claude Code

Tellonce

Version **1.7.0** moves opt-in automatic learning to user prompts and keeps unresolved memory questions in the background. It also adds explicit, namespaced selection, execution-support, publication and frozen-test APIs for host integrations. These APIs require a host to supply model calls and execution events; installing the plugin does not automatically enable that experimental pipeline. See [release notes](docs/releases/1.7.0.md).

**English** · [中文](README.zh.md)

[](https://arxiv.org/abs/2606.13174) [](LICENSE)

Stop re-explaining yourself to your AI coding agent. Tellonce remembers the corrections you make and — when you ask it to — enforces them, so the same mistake doesn't come back. In our evaluations, held-out preference violations drop from **100% to 2.0%** on out-of-distribution coding-agent tasks ([research below](#-the-research-behind-it)).

You told your agent to stop writing scratch files to `/tmp`. To reply in your language. To leave unrelated code alone. Three turns later it does it again. Tellonce can scan turns for preferences, pitfalls, and workflow rules, record them in a shared local store, and hard-enforce the ones you care about.

It is **non-blocking and privacy-conservative by default**: installation enables local rule retrieval, but automatic model-backed memory upsert and hard enforcement are both off. Enable memory upsert explicitly with `memory_upsert.py enable-hooks`; it then sends a redacted copy of each complete user turn to the current platform's CLI model in a detached worker. The separate per-reply shadow judge also remains off until enabled.

✨ Highlights

• 🧠 Learns from your corrections when enabled. Automatic memory upsert is opt-in; local retrieval works without a model call.
• 🛡️ Opt-in enforcement. Turn it on and replies that violate your saved rules ar