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 wkin-t/claude-copilot-plugin --skill copilot-runtimegit clone --depth 1 https://github.com/wkin-t/claude-copilot-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/wkin-t/claude-copilot-plugin/copilot-runtime)<a href="https://agentmods.dev/skills/wkin-t/claude-copilot-plugin/copilot-runtime"><img src="https://agentmods.dev/badge/skills/wkin-t/claude-copilot-plugin/copilot-runtime/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/wkin-t/claude-copilot-plugin/copilot-runtime"><img src="https://agentmods.dev/badge/skills/wkin-t/claude-copilot-plugin/copilot-runtime.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 | $0.00039 | $0.00708 |
| Opus 5.5 | $0.00016 | $0.00283 |
| Sonnet 5.5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
copilot-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot CLI Runtime
Use this skill only inside copilot-cli:copilot-task and copilot-cli:copilot-review subagents.
Invocation Template
Always use a temporary file to pass the prompt — this avoids shell injection when file contents are embedded.
Run the Bash call with run_in_background: true, then immediately use Monitor to stream the result. Never use sleep, until loops, or output-file polling to wait for completion.
_prompt_file=$(mktemp /tmp/copilot-prompt-XXXXXX.txt)
cat > "$_prompt_file" << 'PROMPT_EOF'
<task_prompt>
PROMPT_EOF
copilot -p "$(cat "$_prompt_file")" \
--model <model> \
[--effort <effort>] \
-s \
--allow-all \
[--add-dir <working_dir>]
rm -f "$_prompt_file"
With -s (silent), copilot emits output only once at completion — Monitor fires exactly when the result is ready, with no wasted polling rounds.
Required Flags
| Flag | Purpose |
|---|---|
-s / --silent |
Only output model response, suppress stats |
--allow-all |
Grant all permissions for non-interactive mode. Grants Copilot CLI full tool access — do not use in untrusted environments |
Model Routing
| Model | Used by | Strengths |
|---|---|---|
claude-sonnet-4-6 |
copilot-task (fixed) |
Context-heavy delegation, exploration, architecture |
gpt-5.4 |
copilot-review (fixed) |
Edge cases, boundary conditions, adversarial review |
gpt-5-mini |
Debug only — never for real tasks | Plugin testing |
Agents hard-code their model choice; do not override. Default --effort high for all real tasks.
Context Injection
⚠️ Privacy notice: Copilot CLI auto-loads
./CLAUDE.mdand./.claude/CLAUDE.mdfrom the working directory and sends them to GitHub Copilot (Microsoft/OpenAI servers). If your CLAUDE.md contains internal system prompts, proprietary constraints, or sensitive business context, run from a clean directory or ensure your CLAUDE.md is safe to share externally.
For additional context (memory, file contents): embed directly in the prompt inside <context> tags.
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 · 73 lines · 39 tokens per session scan A ccb6c030b0cf
copilot-runtime is a skill published in the GitHub repository wkin-t/claude-copilot-plugin (4 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 708 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.
copilot-runtime compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copilot-runtimewkin-t/claude-copilot-plugin | Skill | 4 | 6mo ago | MIT | A | 39 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |