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/greenpolo/cc-multi-cli-plugin/multi-plan-handoffnpx skills add greenpolo/cc-multi-cli-plugin --skill multi-plan-handoffgit clone --depth 1 https://github.com/greenpolo/cc-multi-cli-pluginWhat 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 | $0.00029 | $0.01362 |
| Opus 5 | $0.00015 | $0.00681 |
| Sonnet 5 | $0.00006 | $0.00272 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
multi-plan-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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-CLI Plan Handoff
When the user asks to delegate work to a multi:* execute/delegate subagent (multi:codex-execute, multi:cursor-delegate, multi:opencode-delegate, or any future execute/delegate subagent), you must check whether a plan file exists in conversation context. If one does, dispatch the subagent with --plan <path> and never paste the plan's content into the Agent tool's prompt.
The reason: every paraphrasing layer (you summarizing the plan, the Sonnet wrapper prepending framing, the upstream CLI re-reading prose) loses fidelity. --plan <path> makes the upstream CLI read the file directly — bytes-identical, zero rewriting.
Detection — when is there a plan in context?
Scan recent conversation for these signals, in priority order:
-
Plan mode
Plan File Infoblock. When Claude Code's plan mode is or was active, system reminders contain a line like:You should create your plan at C:\Users\<user>\.claude\plans\<slug>.mdThat path is canonical even afterExitPlanMode— the file persists. If you see this in any system reminder this session, treat it as the active plan file. -
Superpowers
writing-plansoutput. Thesuperpowers:writing-plansskill writes plan files to a known location and announces the path in its output. If you used or saw it this session, that path is in scope. -
Explicit user reference. Any path the user typed or that you wrote that matches one of:
*/.claude/plans/*.md*/plans/*.md(project-local plans)- A path the user explicitly called "the plan" or "the spec"
-
A plan you just authored. If you wrote a markdown file in this session whose path includes
/plans/and whose contents are step-by-step instructions, that's a plan.
Trigger phrases
Apply this skill when the user says any of these (case-insensitive, fuzzy):
- "execute it via codex" / "send to codex" / "delegate to codex" / "have codex implement this" / "codex it"
- "execute via cursor" / "send to cursor" / "delegate to cursor" / "cursor it"
- "execute via opencode" / "send to opencode" / "delegate to opencode" / "opencode it"
- "execute the plan" (with no path — auto-resolve from context)
- Any explicit "/codex:execute", "/cursor:delegate", or "/opencode:delegate" with no inline prompt text
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.
- 2d ago First seen · 85 lines · 29 tokens per session scan A 141961013d21
multi-plan-handoff is a skill published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 16d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,362 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 2026-08-30.
Other skills, from other repositories
copilot-pr-review-loop
Drive a GitHub pull request through repeated rounds of Copilot code review until convergence. Use when the user asks to "request Copilot review", "run a Copilot review loop", iterate on Copilot feedback, or wants automated triage-and-respond on Copilot PR comments. Covers re-request mechanics, open-thread filtering…
upstream-sync
Periodically sync new commits from microsoft/terminal into this manually-forked intelligent-terminal repo by cherry-picking commit-by-commit onto a dated sync branch, auto-skipping revert pairs and empty commits, auto-resolving known take-upstream files, and stopping cleanly on genuine conflicts. The agent (you…
release-notes
Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…
add-acp-agent-support
Add first-class support for an ACP-compatible agent CLI to Intelligent Terminal. Use when integrating a new built-in AI agent, ACP server command, authentication flow, model selection, interactive delegation, session hooks, onboarding, Settings, branding, GPO policy, documentation, tests, build, deployment, or live…
opentag
Use when installing, pairing, operating, or troubleshooting OpenTag through the published CLI, self-hosted Control Plane, governed completion, supported collaboration platforms, or built-in coding agents.
pr-integration-test
Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.