Borrowing it
Nothing to install: this file belongs to AIOSAI/AIPass. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AIOSAI/AIPass/main/.codex/skills/claude/SKILL.mdgit clone --depth 1 https://github.com/AIOSAI/AIPassWrote 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/aiosai/aipass/claude)<a href="https://agentmods.dev/skills/aiosai/aipass/claude"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/claude/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/aiosai/aipass/claude"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/claude.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 | $0.00070 | $0.01094 |
| Opus 5.5 | $0.00028 | $0.00438 |
| Sonnet 5.5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
claude 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 today.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switch to Claude Code
Purpose: move this chat from Codex to Claude Code in one turn, in this same terminal. It is still you: memories saved, the live thread written down, Claude opens where you stood. Works like a compaction, except the next model reads the summary.
Execution
-
Pin the live thread FIRST — one sentence: what this chat was doing when the switch was asked (the task, question or build mid-flight; "nothing in flight" counts). It becomes the Resuming line.
-
Prep, compact form. Do the memory steps of
.agents/skills/prep/SKILL.md(session entry, key learnings, todos reconciled, observations if any) and update any plan this chat touched. Skip the git suggestion; note uncommitted files in the handoff instead. -
Write the handoff to
.ai_mail.local/handoff.md(untracked, beside the session pointer). Overwrite; one file, the latest switch. The whole file is the first prompt Claude receives, so write it to the next model, in this shape:Hi. You are <branch>, the same citizen, continuing a chat that just moved from Codex to Claude Code on the user's /claude. Run your startup protocol first (memories one file per call, dashboard refresh, inbox), then read this handoff and pick up the Resuming line. Say in one line that you are here and what you are on; no recap. ## Handoff from Codex, <date time> Primary request and intent: what the user asked for, in their words where it matters. Decisions made: rulings, with who made them. Files touched: paths; which are committed, which are not. In flight: dispatches out (ids), sub-agents, background work, open mails. Errors met and how they ended. Current work: where exactly the chat stood. Resuming: the step-0 line, then the next concrete action.Facts only, no praise, no narration. Under 2,500 words. The next model has your memories; the handoff carries what memories do not: the live thread.
-
Switch. Run in the shell. The model:
fablewhen the branch is devpulse,opusfor every other branch (the owner's rule: Fable is devpulse's seat only).
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.
- today Changed 98a5005dd993
- yesterday First seen · 43 lines · 70 tokens per session scan A 2c341ecb9452
claude is a skill published in the GitHub repository AIOSAI/AIPass (306 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,094 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 2026-10-27.
Other skills, from other repositories
efficient-execution
Reduce token waste and task completion time by choosing the simplest tool for each job.
process-capture
Capture successful multi-step workflows as reusable skills so future sessions can replay them.
task-planning
Match planning effort to task complexity. Check existing skills before inventing a new approach.
learning-capture
Log corrections, errors, and discoveries to orbital/LESSONS.md so future sessions avoid repeating mistakes.
aura
Give this agent a real email address, a webhook URL, durable memory across runs, and the ability to wait for an event without burning tokens. Use when a task needs a verification code sent by email, needs to wait for a webhook or an approval, needs to remember something after the session ends, or needs to survive a…
security-audit
Auditoria de segurança aplicada (AppSec). Varre código, dependências e configurações contra OWASP Top 10 / CWE Top 25, identifica segredos expostos, valida controles de auth/authz e gera relatório priorizado. Use para "revisar segurança", "auditar vulnerabilidades", "threat modeling" ou "security review".