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.
npx agentmods add skills/yujunzhou/tellonce/codexnpx skills add YujunZhou/tellonce --skill codexgit clone --depth 1 https://github.com/YujunZhou/tellonceWrote 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.
[](https://agentmods.dev/skills/yujunzhou/tellonce/codex)<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>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.
| Model | Per session | Once 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 |
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.
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.
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=true或PT_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-hooks;disable-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.jsonand 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, ornone. - 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 scanwhen installed. - Wrap any subprocess that produces user-facing output via
tellonce_codex exec -- <cmd>so its stdout is verified and audited.
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.
- .codex-plugin/plugin.json 1.3 KB
- dashboard.sh 348 B runs code
- docs/CC_PARITY_MATRIX.md 7.3 KB
- docs/README.md 3.2 KB
- doctor.sh 345 B runs code
- hooks/hooks.json 714 B
- hooks/posttooluse-deterministic-block.sh 2.0 KB runs code
- hooks/sessionstart-init.sh 1.9 KB runs code
- hooks/userpromptsubmit-dispatch.py 2.6 KB runs code
- hooks/userpromptsubmit-memory-upsert.sh 326 B runs code
- hooks/userpromptsubmit-pending-inject.sh 2.0 KB runs code
- hooks/userpromptsubmit-retrieve-inject.sh 3.1 KB runs code
- hooks/userpromptsubmit-shadow-alert-inject.sh 1.2 KB runs code
- install.sh 14 KB runs code
- shared_lib/_install_merge_settings.py 12 KB runs code
- shared_lib/_pt_hooks.txt 407 B
- shared_lib/detect_user_prefer.py 7.2 KB runs code
- shared_lib/deterministic_block.py 9.3 KB runs code
- shared_lib/fingerprints.yaml 1.1 KB
- shared_lib/memory_judge.py 48 KB runs code
- shared_lib/memory_store.py 86 KB runs code
- shared_lib/memory_upsert_hook.py 4.3 KB runs code
- shared_lib/memory_upsert.py 45 KB runs code
- shared_lib/path_config.py 13 KB runs code
- shared_lib/pending_queue_manager.py 23 KB runs code
- shared_lib/pt_platform.py 1.3 KB runs code
- shared_lib/redaction.py 3.4 KB runs code
- shared_lib/retrieve_inject.py 59 KB runs code
- shared_lib/shadow_alert_inject.py 6.1 KB runs code
- shared_lib/transcript_adapter.py 7.9 KB runs code
- shared_lib/verify_compliance.py 24 KB runs code
- shared_lib/verify_retry_shadow.py 27 KB runs code
- skills/tellonce/SKILL.md 12 KB
- tellonce_codex/__init__.py 52 B runs code
- tellonce_codex/__main__.py 49 B runs code
- tellonce_codex/cli.py 6.8 KB runs code
- tellonce_codex/codex_posttooluse_block.py 11 KB runs code
- tellonce_codex/dashboard.py 3.4 KB runs code
- tellonce_codex/doctor.py 11 KB runs code
- tellonce_codex/index.py 1.8 KB runs code
- tellonce_codex/install_codex_hooks.py 15 KB runs code
- tellonce_codex/install.py 3.1 KB runs code
- tellonce_codex/ledger.py 17 KB runs code
- tellonce_codex/memory.py 5.3 KB runs code
- tellonce_codex/migrate.py 1.3 KB runs code
- tellonce_codex/mode.py 2.3 KB runs code
- tellonce_codex/paths.py 8.6 KB runs code
- tellonce_codex/promote.py 4.4 KB runs code
- tellonce_codex/scan.py 2.6 KB runs code
- tellonce_codex/uninstall.py 1.7 KB runs code
- tellonce_codex/verify.py 5.3 KB runs code
- tellonce_codex/wrapper.py 12 KB runs code
- uninstall.sh 4.6 KB runs code
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.
- 6d ago First seen · 156 lines · 25 tokens per session scan A eb8b101c24d4
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.
Other skills, from other repositories
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
knowledge-priming-refiner
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create…
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.
alive-inbox
Scan 03Inbox/ for unrouted files, present routing suggestions.