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 jxpeng98/qiongli --skill no-qiongligit clone --depth 1 https://github.com/jxpeng98/qiongliWrote 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/jxpeng98/qiongli/no-qiongli)<a href="https://agentmods.dev/skills/jxpeng98/qiongli/no-qiongli"><img src="https://agentmods.dev/badge/skills/jxpeng98/qiongli/no-qiongli/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/jxpeng98/qiongli/no-qiongli"><img src="https://agentmods.dev/badge/skills/jxpeng98/qiongli/no-qiongli.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 | $0.00070 | $0.00360 |
| Opus 5 | $0.00035 | $0.00180 |
| Sonnet 5 | $0.00014 | $0.00072 |
| Haiku 4.5 | $0.00007 | $0.00036 |
Grade A, and why
no-qiongli 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 today.
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
NoQiongli · 仅回复
Answer the user's request using only material already visible in the conversation. This entry is self-contained: do not load the main Qiongli Skill, a workflow, reference, catalog or another Skill to use it.
Do not call tools, programs, MCP, search, resource readers or other agents. Do not read or write files, check connections, start project runs, save summaries or refresh the Graph. Return explanations, proposed text or suggested commands in chat only; do not execute them. If required material is not visible, explain the gap or ask the user to paste it. Never imply that unseen content was read or that a search, independent review, saved artifact or formal quality gate was completed.
Keep reply-only active in this conversation until the user explicitly resumes execution, unless they limited it to one reply. Do not save a mode setting or call a tool to enter or leave it. A bare “no”, quoted material, an entry name mentioned as a topic, or a Hook reminder does not select or cancel this mode. On explicit resumption, ordinary routing and existing permissions apply to the authorized task.
This is Skill guidance, not a Host tool lock. It does not override higher-priority instructions, cancel running work or disable automatic Host hooks. Do not claim that tools or hooks have been technically disabled.
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.
- today First seen · 28 lines · 70 tokens per session scan A 3c0dd68bc309
no-qiongli is a skill published in the GitHub repository jxpeng98/qiongli (25 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 360 once invoked, about $0.0003 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 2026-09-14.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).