Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mvpasarel/gh-copilot-plugin-cc/plugin install copilotWrote 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/commands/mvpasarel/gh-copilot-plugin-cc/adversarial-plan-review)<a href="https://agentmods.dev/commands/mvpasarel/gh-copilot-plugin-cc/adversarial-plan-review"><img src="https://agentmods.dev/badge/commands/mvpasarel/gh-copilot-plugin-cc/adversarial-plan-review/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/commands/mvpasarel/gh-copilot-plugin-cc/adversarial-plan-review"><img src="https://agentmods.dev/badge/commands/mvpasarel/gh-copilot-plugin-cc/adversarial-plan-review.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 | $0.00012 | $0.00651 |
| Opus 5 | $0.00006 | $0.00326 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
adversarial-plan-review 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 10d 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.
What it actually says
Run an adversarial review of an implementation plan via Copilot. Position it as a challenge review that questions the chosen approach, ordering, risk coverage, and hidden assumptions. It is not just a stricter pass over plan completeness.
Raw slash-command arguments:
$ARGUMENTS
Core constraint:
- This command is review-only.
- Do not fix issues in the plan, apply patches, or suggest that you are about to make changes.
- Your only job is to run the review and return Copilot's output verbatim to the user.
- Keep the framing focused on whether the plan's assumptions are sound, what it depends on implicitly, and where it would fail under real-world execution.
Execution mode rules:
- If the raw arguments include
--background, do not ask. Run in a Claude background job. - If the raw arguments include
--wait, do not ask. Run in the foreground. - Otherwise, estimate adversarial review effort:
- Recommend waiting only when the plan is clearly tiny (1-3 steps, no significant risks mentioned).
- In every other case, including unclear size, recommend background.
- Use
AskUserQuestionexactly once with two options, putting the recommended option first and suffixing its label with(Recommended):Wait for resultsRun in background
Argument handling:
- Preserve the user's arguments exactly.
- Plan content can be passed via
--plan-file <path>, positional arguments, or stdin. - When
--plan-fileis provided, positional arguments become adversarial focus text. - When
--plan-fileis not provided, positional arguments are treated as plan content. Use--focus <angle>to specify the adversarial angle separately. - Do not strip
--backgroundor--waityourself. - Do not weaken the adversarial framing or rewrite the user's focus text.
Foreground flow:
- Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/copilot-companion.mjs" adversarial-plan-review "$ARGUMENTS"
- Return the command stdout verbatim, exactly as-is.
- Do not paraphrase, summarize, or add commentary before or after it.
Background flow:
- Launch with
Bashin the background:
Bash({
command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/copilot-companion.mjs" adversarial-plan-review "$ARGUMENTS"`,
description: "Copilot adversarial plan review",
run_in_background: true
})
- Do not call
BashOutputor wait for completion in this turn. - After launching the command, tell the user: "Copilot adversarial plan review started in the background. Check
/copilot:statusfor progress."
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.
- 10d ago First seen · 58 lines · 12 tokens per session scan A 570df0ee315b
adversarial-plan-review is a command published in the GitHub repository mvpasarel/gh-copilot-plugin-cc (7 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 651 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.