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 GalaxyRuler/Galactic-skills --skill external-agent-handoffgit clone --depth 1 https://github.com/GalaxyRuler/Galactic-skillsWrote 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/galaxyruler/galactic-skills/external-agent-handoff)<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/external-agent-handoff"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/external-agent-handoff/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/galaxyruler/galactic-skills/external-agent-handoff"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/external-agent-handoff.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 | $0.00086 | $0.00865 |
| Opus 5.5 | $0.00034 | $0.00346 |
| Sonnet 5.5 | $0.00017 | $0.00173 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
external-agent-handoff 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Agent Handoff
Overview
The user runs a standing multi-agent workflow: Claude audits, plans, and reviews; Codex implements; an external GPT reviews plans adversarially. The deliverable of an audit or planning session is a handoff prompt, not a commit. Handoff prompts must be self-contained, addressed, precondition-checked, and delivered ready to paste — every time, without being asked.
When to use
Use this when:
- The user asks for "a prompt for Codex/ChatGPT/GPT/Gemini" or an external review of a plan.
- A slice, phase, plan, or decision closes and implementation belongs to Codex.
- You are auditing or reviewing work another agent implemented.
Role contract
- In audit/review/planning sessions, do not implement. Produce findings, plans, and handoff prompts. Only implement when the user explicitly reassigns the role.
- When a slice or decision closes, draft the next handoff prompt automatically. Never end the turn with "want me to draft it?" — draft it.
Workflow
- Address the prompt
- Start the prompt with an explicit destination header: which agent, which project/session it must be pasted into.
- For Codex: name the target repo's full absolute path and expected branch at the top.
- This prevents wrong-session pastes and cross-project contamination.
- Make it fully self-contained
- Assume the recipient has zero access to this session, this machine's files, or prior context.
- Inline everything needed: the full plan text, relevant diffs, specs, constraints, decisions. Never reference "the plan above" or a local file a cloud model cannot open.
- For cloud models with upload limits, state the limit handling: inline text, or a bundle within the size limit.
- If using a prompt template, fill every placeholder. An empty placeholder costs a full round-trip.
- Verify preconditions before pinning them
- If the prompt pins a base commit or branch state, verify it is current first (
git fetch, confirm HEAD) — stale pinned bases repeatedly block Codex runs. - Include a fallback instruction for the recipient if the base has moved.
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.
- 2mo ago First seen · 68 lines · 86 tokens per session scan A aa4caa481c27
external-agent-handoff is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 865 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 2026-09-06.
external-agent-handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| external-agent-handoffGalaxyRuler/Galactic-skills | Skill | 5 | 2mo ago | MIT | A | 86 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |