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 xiaolai/cc-suite/plugin install cc-suiteWrote 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/xiaolai/cc-suite/qwen-preflight)<a href="https://agentmods.dev/commands/xiaolai/cc-suite/qwen-preflight"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/qwen-preflight.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 5.1 | $0.00020 | $0.00400 |
| Opus 5 | $0.00010 | $0.00200 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
qwen-preflight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Qwen Review Preflight
Step 1: Run the preflight script
bash "${CLAUDE_PLUGIN_ROOT}/scripts/qwen-preflight.sh"
Parse the single JSON object. If status is "error", skip to Step 3.
Step 2: Display results
Display:
## Qwen Review Preflight
**Status**: {status}
**Qwen version**: {qwen_version}
**Minimum supported version**: {minimum_version}
**Authentication**: not probed
**Sandbox provider**: {sandbox_provider}
### Runner guarantees
- Safe Mode
- Plan mode
- Qwen sandbox
- isolated temporary target copies
- explicit non-review tool denials and verified init tool surface
- zero tool-call budget for prompt-only reviews
- bounded `read_file` calls for declared targets
- stream-json completion validation
- exact-target read policy
- bounded session resume
auth_mode is deliberately "not_probed": authentication requires a real
provider call, and preflight must not send an availability prompt. The first
real review reports an authentication/provider failure through the job result.
Step 3: Handle errors
Report error_code and error, then apply the matching remedy:
qwen_not_found— install Qwen Code and ensureqwenis onPATH.qwen_version_unsupported— upgrade to the reported minimum version or newer.qwen_version_unparseable— the installed binary did not return a usable version.qwen_sandbox_unavailable— install or configure sandbox-exec, Docker, or Podman.
Do not run the review runner when preflight returns status: "error".
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 · 58 lines · 20 tokens per session scan A 17bfd88e570e
qwen-preflight is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 5d ago), licensed ISC. It adds 20 tokens to every session and 400 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
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.