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 Beaulewis1977/claude-plugin-for-codex --skill claude-transfergit clone --depth 1 https://github.com/Beaulewis1977/claude-plugin-for-codexWrote 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/beaulewis1977/claude-plugin-for-codex/claude-transfer)<a href="https://agentmods.dev/skills/beaulewis1977/claude-plugin-for-codex/claude-transfer"><img src="https://agentmods.dev/badge/skills/beaulewis1977/claude-plugin-for-codex/claude-transfer/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/beaulewis1977/claude-plugin-for-codex/claude-transfer"><img src="https://agentmods.dev/badge/skills/beaulewis1977/claude-plugin-for-codex/claude-transfer.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 | $0.00043 | $0.00442 |
| Opus 5.5 | $0.00017 | $0.00177 |
| Sonnet 5.5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
claude-transfer 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 2mo 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.
What it actually says
Claude Transfer
Transfer is a structured semantic handoff because Claude Code cannot natively import a Codex transcript turn by turn.
Handoff packet
Create a concise packet with these headings:
- Goal and current user request
- Requirements and constraints
- Decisions and their rationale
- Work completed
- Repository and relevant-file context
- Verification already performed
- Unresolved issues
- Recommended next action
Use --source for an explicitly selected packet file; otherwise send the
handoff over stdin. Never scrape or claim to reproduce the full chat.
Workflow
- Resolve
<plugin-root>/scripts/claude-companion.mjsto an absolute path. - Make exactly one runtime invocation. Runtime action:
transfer. - Classify routine or bounded handoffs as normal, substantial reasoning as
hard, and the most complex or high-stakes handoffs as very-hard. Pass that
classification with
--tier; explicit model and effort selections always win. Pass--cwdwith the current workspace and--jsonas separate arguments. Honor explicit timeout choices. The runtime always creates a fresh session. - Write the free-form handoff to stdin unless using
--source. Never place handoff text in an option, argument, or shell command. Use an argument array; never concatenate or interpolate values into a shell command. Use the execution tool's separate stdin channel; if it exposes an interactive process session, send the text there and explicitly close stdin before waiting. - Keep this read-only. The runtime forces plan permission and safe-mode. Never edit, write, fix, or apply changes, and do not request bypass permissions.
- Require only acknowledgement and readiness, not implementation. Return the
session ID and exact continuation form
claude --resume <session-id>.
What ships with it
1 file 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.
- 2mo ago First seen · 48 lines · 43 tokens per session scan A 56c5618735f8
claude-transfer is a skill published in the GitHub repository Beaulewis1977/claude-plugin-for-codex (3 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 442 once invoked, about $0.0002 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 2026-08-31.
claude-transfer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-transferBeaulewis1977/claude-plugin-for-codex | Skill | 3 | 3mo ago | MIT | A | 43 | Codex |
| taiyi-ui-designDong90/oh-my-taiyiforge | Skill | 855 | today | MIT | A | 35 | Claude Code, Codex |
| taiyi-evolveDong90/oh-my-taiyiforge | Skill | 855 | today | MIT | A | 37 | Claude Code, Codex |
| taiyi-diagram-c4Dong90/oh-my-taiyiforge | Skill | 855 | today | MIT | A | 48 | Claude Code, Codex |
| flow-next-tracker-syncgmickel/flow-next | Skill | 725 | today | MIT | A | 44 | Claude Code, Codex |
| writing-styleumputun/cc-thingz | Skill | 497 | 13d ago | MIT | A | 52 | Claude Code |
| flow-next-primegmickel/flow-next | Skill | 725 | today | MIT | A | 31 | Claude Code, Codex |