English · 中文

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.

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 watches each turn, records the preferences, pitfalls, and workflow rules it detects, and can hard-enforce the ones you care about.

It is safe by default: out of the box it only records and reminds. It never blocks you and never sends your conversation anywhere until you opt in.

• 🧠 Learns from your corrections. Every turn is scanned for preference / pitfall / friction signals and recorded automatically.
• 🛡️ Opt-in enforcement. Turn it on and replies that violate your saved rules are blocked, and the agent fixes them in the same turn.
• 🔒 Private by default. All records stay on your machine, and the optional LLM judge is off by default — when enabled it only ever sees a redacted snippet and runs through your own subscription. (Once you have saved rules, rule retrieval also runs through your own subscription's small model; set PT_RETRIEVE_BACKEND=keyword to keep even that fully local.)
• ⚡ One-command install for GitHub Copilot CLI. Also runs on Claude Code and Codex.
• 🎛️ Three modes, one switch: observe → enforce → full.

Prerequisites: GitHub Copilot CLI and Python 3.7+. Everything else is automatic. Restart Copilot after install. The command is pinned to the immutable release tag v1.2.0, so a later change to main can't alter what you run.

Windows (PowerShell)

powershell -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/YujunZhou/tellonce/v1.2.0/copilot/bootstrap.ps1 | iex"

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/YujunZhou/tellonce/v1.2.0/copilot/bootstrap.sh | bash

This downloads the plugin, copies it into Copilot's plugin directory, installs the optional dependency, registers it with Copilot (so the hooks load), sets the safe observe mode, and records your Python path. Then restart Copilot.

Cautious? Verify the script before piping it to a shell — see copilot/README.md for the published SHA256 of each bootstrap script.

All three share the same user-preference memory and design philosophy (Iron Law / Gate Function / scan → record → confirm). The underlying mechanism is adapted per runtime: Claude Code and Copilot use Stop hooks, while Codex has no Stop hook and runs through a wrapper instead. See codex/docs/CC_PARITY_MATRIX.md.

Switch at any time (Copilot variant):

python "<plugin>/lib/pt_mode.py" observe   # back to the safe default
python "<plugin>/lib/pt_mode.py" enforce   # turn on hard blocking
python "<plugin>/lib/pt_mode.py" full      # hard blocking + LLM judge
python "<plugin>/lib/pt_mode.py" status    # show the current mode

Privacy: all records stay local in every mode. Only full sends the last message and reply (redacted) to copilot -p for scoring, on your own subscription. Rule retrieval (once you have saved rules) also runs through your own subscription's small model; PT_RETRIEVE_BACKEND=keyword keeps it fully local. The full judge additionally needs PT_SHADOW_RULE_IDS set to the rule ids you want checked — pt_mode.py full prints a reminder.

1. Session start — your saved rules relevant to the current project are injected into the agent's context.
2. Each turn ends (Stop) — the turn is scanned for new preference / pitfall / friction signals, which are recorded to an observation log.
3. In full — a small-model LLM judge checks each reply against the rules you list in PT_SHADOW_RULE_IDS and flags violations for the agent to fix. (The enforce deterministic layer ships with no built-in rules — it is an opt-in extension point, so it blocks no content by itself.)

python "<plugin>/lib/doctor.py"        # self-check: python / registration / mode / hooks
python "<plugin>/lib/dashboard.py"     # status at a glance: mode / rules / records
python "<plugin>/lib/uninstall.py"     # dry-run: show what would be removed
python "<plugin>/lib/uninstall.py --all"
copilot plugin uninstall tellonce

<plugin> is printed at the end of install; it is ~/.copilot/installed-plugins/tellonce/tellonce.

README.md                 # this landing page (English)
README.zh.md              # Chinese companion
copilot/                  # GitHub Copilot CLI variant — the public release
codex/                    # Codex variant (wrapper-driven)
docs/claude-code.md       # Claude Code variant, in depth
hooks/ lib/ SKILL.md ...  # Claude Code variant (lives at the repo root)
seed_memory/              # empty by default; new users start with a blank slate
LICENSE

MIT — see LICENSE. An open-source research artifact for studying in-session LLM preference enforcement. Issues and PRs welcome.