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 josephyaduvanshi/qwen-companion/plugin install qwenWrote 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/josephyaduvanshi/qwen-companion/adversarial-review)<a href="https://agentmods.dev/commands/josephyaduvanshi/qwen-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/josephyaduvanshi/qwen-companion/adversarial-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/josephyaduvanshi/qwen-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/josephyaduvanshi/qwen-companion/adversarial-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 | $0.00013 | $0.00366 |
| Opus 5 | $0.00006 | $0.00183 |
| Sonnet 5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
adversarial-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Before running, estimate the review size so we can decide between foreground and background.
Quick size check:
git status --short | head -40
git diff --shortstat
git diff --shortstat --cached
If the change is small, prefer foreground. If it is large or ambiguous, ask the user:
Run now and wait (--wait) (Recommended for small changes)Run in the background (--background)
Then run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/qwen-companion.mjs" adversarial-review "$ARGUMENTS"
Output rules:
/qwen:adversarial-reviewbuilds a strict adversarial review prompt, passes the repository context to Qwen, and enforces a JSON-schema'd response (verdict, summary, findings with severity/file/line ranges, next steps).- The companion renders the structured response as Markdown sorted by severity.
- Present the command output verbatim to the user.
- Do not paraphrase, summarize, or add commentary.
- After presenting findings, STOP. You MUST explicitly ask the user which findings, if any, to fix before touching code. Auto-applying adversarial fixes is forbidden even if the fix looks obvious.
- Extra positional text is forwarded as focus instructions (e.g.
/qwen:adversarial-review look for race conditions around cache invalidation).
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.
- 12d ago First seen · 36 lines · 13 tokens per session scan A 4170bc5c7b1e
adversarial-review is a command published in the GitHub repository josephyaduvanshi/qwen-companion (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 366 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.