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 skills add CHENyiru3/AI-Skills-Collections --skill linux-codex-backupgit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote 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/chenyiru3/ai-skills-collections/linux-codex-backup)<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/linux-codex-backup"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/linux-codex-backup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/linux-codex-backup"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/linux-codex-backup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.00411 |
| Opus 5.5 | $0.00025 | $0.00164 |
| Sonnet 5.5 | $0.00013 | $0.00082 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
linux-codex-backup 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 yesterday.
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.
What it actually says
Linux Codex backup
Use the codex-backup skill and its bundled exporter. Install both skills as sibling directories. Read the Linux setup for the verified yiru-linux baseline, commands, and service constraints; recheck paths on another host.
Honor CODEX_HOME and CODEX_SQLITE_HOME. The exporter also accepts --codex-home and --sqlite-home; pass the latter when config.toml sets sqlite_home, because the exporter does not read that configuration. Read live SQLite databases through the exporter; do not copy database files without their WAL state.
Preview locally, check the intended account and transcript scope, then sync only to the user's authorized private archive. New Linux transcripts have the Linux tag and sync commits carry [Linux]. Keep an existing archive's timezone and fuller transcripts when sharing it with another machine.
Publish backup commits directly to the private archive's default branch and verify the pushed commit. For authorized changes to these skills in AI-Skills-Collections, also commit and push directly to its default branch. That public collection holds skill code and documentation; keep transcripts, profiles, credentials, and archive checkouts outside it.
Use snapshot and sync for manual backups. The shared runner's install action creates a macOS LaunchAgent and cannot install a Linux schedule. Only configure a systemd user service/timer when scheduling is requested; use absolute paths, include the user's GitHub CLI directory in PATH, and verify authentication in the service environment.
What ships with it
2 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.
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.
- yesterday First seen · 19 lines · 63 tokens per session scan A 9ea196d5211d
linux-codex-backup is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 411 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-13.
linux-codex-backup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| linux-codex-backupCHENyiru3/AI-Skills-Collections | Skill | 2 | 3d ago | MIT | A | 63 | Claude Code, Codex |
| recall-sessiontobihagemann/turbo | Skill | 420 | 2d ago | MIT | A | 45 | Claude Code |
| memorix-git-memoryAVIDS2/memorix | Skill | 934 | 3d ago | Apache-2.0 | A | 31 | Claude Code |
| change-boottikalk/adlc-team-skills | Skill | 145 | 2d ago | MIT | A | 113 | Claude Code, Codex |
| session-wrapuploopdive/js2 | Skill | 67 | today | Apache-2.0 | A | 54 | Claude Code |
| catchupAvijit07x/claude-db | Skill | 235 | 8d ago | Apache-2.0 | B | 71 | Claude Code, Codex |
| updatememtomem/memtomem | Skill | 24 | today | Apache-2.0 | A | 29 | Claude Code |