tellonce

tellonce is a skill for Claude Code, Codex from YujunZhou/tellonce. It costs 25 tokens per session (2,870 once invoked), scanned A, original, MIT.

A preference and memory manager for coding-agent conversations. It records user preferences in a shared project store and applies them across supported platforms.

In plain words
What is it for?
It is for saving, updating, retiring, restoring, and auditing durable user preferences, with optional automatic processing of new messages.
Why use it?
It keeps preferences consistent between conversations while requiring recorded changes to include evidence from the user's message.

Skill for Claude CodeCodex

Written for Claude Code and Codex: UserPromptSubmit hook event, but also runs codex exec. Also seen: mentions Claude Code; mentions Codex.

Part of the tellonce plugin — 2 skills, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/yujunzhou/tellonce/codex
Any agent
npx skills add YujunZhou/tellonce --skill codex
Clone the repo
git clone --depth 1 https://github.com/YujunZhou/tellonce

Made for: Claude Code, Codex.

Or install tellonce, the plugin that ships this one along with the rest of its 2 skills, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tellonce

README.md
[![agentmods](https://agentmods.dev/badge/skills/yujunzhou/tellonce/codex.svg)](https://agentmods.dev/skills/yujunzhou/tellonce/codex)
Your own site
<a href="https://agentmods.dev/skills/yujunzhou/tellonce/codex"><img src="https://agentmods.dev/badge/skills/yujunzhou/tellonce/codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.02870
Opus 5 $0.00013 $0.01435
Sonnet 5 $0.00005 $0.00574
Haiku 4.5 $0.00003 $0.00287

Measured 6d ago against content hash eb8b101c24d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tellonce scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 46 executable files (dashboard.sh, doctor.sh, hooks/posttooluse-deterministic-block.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

codex/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tellonce for Codex

统一记忆 Upsert

  • 三个平台共用 <project_root>/.tellonce/memory/。SQLite 是唯一真值;旧的 .codex/tellonce/memories/active 只作为首次迁移来源。
  • 持久偏好只能通过 shared_lib/memory_upsert.py enqueue 入队;agent 主动记录使用 python <skill_dir>/shared_lib/memory_upsert.py enqueue --manual --force --source-text "<完整原始用户消息>",自动 hook 已启用时会跳过重复入队。复杂多行消息可改用 --request-file <json>。禁止直接写 active Markdown。
  • UserPromptSubmit 自动 upsert 默认关闭;启用后前台只写 inbox 并启动 detached worker,立即返回。LLM 判断(NOOP|UPDATE|SUPERSEDE|SPLIT|NEW|REJECT|ARCHIVE|RESTORE)与 SQLite 提交都在后台进行,任何失败都不能阻塞用户。
  • 每个 mutation/child 必须携带本轮完整用户原话中的精确 evidence_spans;危险 durable rule 使用 REJECT,明确停用规则使用事务化 ARCHIVE,恢复 archived rule 使用 RESTORE
  • judge 在返回 NEEDS_USER 前,先用当前项目根目录、最近对话和 active rules 消解指代、scope 与 activation;这些 context 只能帮助解释本轮用户原话,不能单独授权持久化。只有剩余歧义会改变未来行为时才进入轻量 clarification 队列,并在后续上下文中只问一个简短问题;下一条明确回答可关闭对应 turn。
  • 关闭自动 upsert 后 clarification 不再注入;过期项可用 python <skill_dir>/shared_lib/memory_upsert.py dismiss --turn-key <id> 手动移除。
  • 自动 hook 默认关闭。设置 memory_upsert_enabled=truePT_MEMORY_UPSERT_ENABLED=1 后才启用。
  • 一次修改三平台:运行 python <skill_dir>/shared_lib/memory_upsert.py enable-hooksdisable-hooks 关闭,hook-status 查询。

Codex actually exposes the same hook system as Claude Code (PreToolUse / PostToolUse / SessionStart / UserPromptSubmit / PermissionRequest). The codex variant of tellonce installs into ~/.codex/skills/tellonce/

  • ~/.codex/hooks.json and uses native hooks for retrieval + enforcement. The wrapper path (tellonce_codex exec --) is still the way to enforce on the FINAL agent text response (codex doesn't fire a Stop hook for that; PostToolUse only sees tool inputs/outputs).

Core rules (every turn)

  • Scan every user message for preference, pitfall, friction, or none.
  • 应用:只使用 UserPromptSubmit 注入的 canonical active projection;不要读取旧的 <state>/index/active_memories.json
  • Record durable evidence through tellonce_codex scan when installed.
  • Wrap any subprocess that produces user-facing output via tellonce_codex exec -- <cmd> so its stdout is verified and audited.

Read the full file on GitHub · 156 lines

Files

What ships with it

53 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 156 lines · 25 tokens per session scan A eb8b101c24d4

Subscribe to this mod's changes

tellonce is a skill published in the GitHub repository YujunZhou/tellonce (7 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 2,870 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.