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 santiquiroz/copilot-plugin-cc --skill copilot-rescuegit clone --depth 1 https://github.com/santiquiroz/copilot-plugin-ccWrote 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/santiquiroz/copilot-plugin-cc/copilot-rescue)<a href="https://agentmods.dev/skills/santiquiroz/copilot-plugin-cc/copilot-rescue"><img src="https://agentmods.dev/badge/skills/santiquiroz/copilot-plugin-cc/copilot-rescue/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/santiquiroz/copilot-plugin-cc/copilot-rescue"><img src="https://agentmods.dev/badge/skills/santiquiroz/copilot-plugin-cc/copilot-rescue.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 | $0.00072 | $0.00680 |
| Opus 5 | $0.00036 | $0.00340 |
| Sonnet 5 | $0.00014 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
copilot-rescue 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 8d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forward the requested task to GitHub Copilot CLI with one shell command. Do not do the task yourself once Copilot is invoked — return its output.
Command
copilot -p "<task>" -s \
--allow-tool='shell(git:*)' --allow-tool=write \
--deny-tool='shell(rm)' --deny-tool='shell(git push)' --deny-tool='shell(git reset)'
Deny rules win over allow rules, even under --allow-all — this keeps the run non-interactive-capable while blocking destructive/shared-state commands a mechanical task never needs.
Rules
- Preserve the user's task text verbatim in
-p. Do not add commentary or hedging. -s/--silentstrips usage-stats noise so returned stdout is clean.- Add
--model <name>only if the user named a model; otherwise omit (Auto-selection carries a billing discount on routine work). - Add
--add-dir <path>if the task is scoped outside the current working directory; add-C <dir>only if it explicitly targets a different working directory. - Run the command synchronously — wait for it to finish, don't background it.
- If the user says "continue"/"keep going"/"resume" prior Copilot work here, add
--continueinstead of starting fresh. - Do not inspect the repo, grep, or do follow-up work beyond the one forwarded command — Copilot does the task, you relay its output.
- Only use
--autopilotfor genuinely open-ended multi-step tasks, and always pin--max-autopilot-continues <N>(e.g. 8) when you do — Copilot CLI has a known infinite-loop bug on externally-blocked tasks under autopilot (github/copilot-cli#2969).
Known issues to work around
- Autopilot infinite loop (copilot-cli#2969): avoid
--autopilotfor bounded tasks; pin--max-autopilot-continueswhen used. - Resume-after-rate-limit hang: if output contains "rate limit" (case-insensitive) and then goes silent ~10s, kill the process and report failure — do not wait, do not
--continuea rate-limited session.
Quota / failure handling
If the command fails (non-zero exit, auth error, or a rate-limit message), report the error text verbatim instead of retrying silently — the caller decides whether to fall back to another approach or take the task over directly. To probe auth/health first: copilot --version, then copilot -p "Reply with exactly one word: ready" -s --deny-tool=shell --deny-tool=write.
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.
- 8d ago First seen · 41 lines · 72 tokens per session scan A ffd3da4ea388
copilot-rescue is a skill published in the GitHub repository santiquiroz/copilot-plugin-cc (1 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 680 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
microsoft-build
Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or…
speckit-init
Scaffold a Spec Kit (spec-driven development) project for GitHub Copilot by running specify init --integration copilot --integration-options="--skills". USE FOR: starting a new spec-kit project, bootstrapping spec-driven development in an existing repo, installing spec-kit templates/scripts/commands for Copilot. DO…
speckit-bundle
Discover, install, and author Spec Kit bundles via specify bundle. USE FOR: searching/showing/listing bundles, installing/updating/removing a bundle (a curated set of extensions/presets/integrations/workflows), validating a bundle manifest, building a distributable bundle artifact, initializing a project and…
speckit-extension
Manage Spec Kit extensions via specify extension. USE FOR: installing/removing/updating spec-kit extensions, searching the extension catalog, showing extension info, enabling/disabling extensions, setting extension resolution priority, managing extension catalogs. DO NOT USE FOR: presets (use speckit-preset), bundles…
speckit-preset
Manage Spec Kit presets via specify preset. USE FOR: installing/removing presets, searching the preset catalog, showing preset info, resolving which template a preset name maps to, enabling/disabling presets, setting preset resolution priority, managing preset catalogs. DO NOT USE FOR: extensions (use…
speckit-workflow
Manage and run Spec Kit automation workflows via specify workflow. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use…