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-result-handlingnpx skills add greenpolo/cc-multi-cli-plugin --skill multi-result-handlinggit clone --depth 1 https://github.com/greenpolo/cc-multi-cli-pluginWrote 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/greenpolo/cc-multi-cli-plugin/multi-result-handling)<a href="https://agentmods.dev/skills/greenpolo/cc-multi-cli-plugin/multi-result-handling"><img src="https://agentmods.dev/badge/skills/greenpolo/cc-multi-cli-plugin/multi-result-handling.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00860 |
| Opus 5 | $0.00009 | $0.00430 |
| Sonnet 5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
multi-result-handling 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-CLI Result Handling
When a multi:* subagent returns helper output (Codex, Cursor, Antigravity, OpenCode via multi, or any CLI added via multi-cli-anything):
Preserving the helper's structure
- Preserve the helper's verdict, summary, findings, and next-steps sections exactly. Do not paraphrase, re-order, or summarize them in your own words.
- If the helper produced a structured final report (markdown headers like
## Outcome,## Files touched,## Verification,## Notes), surface those sections as the canonical answer. Your commentary, if any, should reference the report — not restate it. - Use the file paths and line numbers exactly as the helper reports them. Do not normalize Windows backslashes to forward slashes or vice versa.
- Preserve evidence boundaries. If the helper marked something as an inference, an uncertainty, or an open question, keep that distinction in your reply.
When the helper's output is messy
Some upstream CLIs stream chain-of-thought tokens interleaved with the final answer. When you see a mix of reasoning prose and a structured final report:
- Present the structured final report as the answer.
- Optionally quote 1–2 short lines of reasoning if they explain a non-obvious choice — never paraphrase the whole stream.
- If there is no structured final section, fall back to presenting the helper's last coherent paragraph as the result and note that explicitly.
Touched files and verification
- If the helper made edits, say so explicitly and list the touched files when the helper provides them.
- If the helper ran shell commands or other verification steps, surface those exit codes and outputs.
- If the helper says it ran something but no exit code or output is visible, flag that gap rather than assuming success.
Failed runs
- If the helper reports a failed run (exit non-zero, or the failure line
<CLI> <role> failed: ...), report the failure with the most actionable stderr lines and stop. Do not turn a failed helper run into a Claude-side implementation attempt. - If the helper was never successfully invoked (binary missing, auth failure, sandbox block), do not generate a substitute answer at all. Direct the user to
/multi:setupand stop. - If the helper reports malformed output, include the most actionable stderr lines and stop there instead of guessing.
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.
- 3d ago First seen · 50 lines · 17 tokens per session scan A a30e926b0742
multi-result-handling is a skill published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 17d ago), licensed Apache-2.0. It adds 17 tokens to every session and 860 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.