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 gongxuanzhang/shengsheng-skill --skill review-regressiongit clone --depth 1 https://github.com/gongxuanzhang/shengsheng-skillWrote 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/gongxuanzhang/shengsheng-skill/review-regression)<a href="https://agentmods.dev/skills/gongxuanzhang/shengsheng-skill/review-regression"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/review-regression/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/gongxuanzhang/shengsheng-skill/review-regression"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/review-regression.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 | $0.00198 | $0.02436 |
| Opus 5 | $0.00099 | $0.01218 |
| Sonnet 5 | $0.00040 | $0.00487 |
| Haiku 4.5 | $0.00020 | $0.00244 |
Grade A, and why
review-regression 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Regression (审核意见回归讨论)
This skill helps users critically process review feedback on a proposal. The core philosophy is: review opinions are input, not orders. Each piece of feedback should be evaluated on its merits — accepted when insightful, pushed back on when unreasonable, and clarified when ambiguous. The goal is a thoughtful, rational discussion that produces a better proposal, not blind compliance.
Language Detection
Detect the user's language from their first message:
- If the user writes in Chinese, conduct the entire workflow in Chinese
- If the user writes in English, use English throughout
- If the user mixes languages, default to Chinese but ask for preference
Core Principles
These principles guide every interaction in this skill. They exist because review processes often go wrong in predictable ways — people either rubber-stamp everything a senior reviewer says, or defensively reject all feedback. Neither produces good outcomes.
1. Don't Blindly Trust Review Opinions
Review feedback is one person's perspective, shaped by their context, assumptions, and biases. A reviewer might:
- Misunderstand the original intent or constraints
- Apply standards from a different domain that don't fit here
- Raise valid concerns but suggest poor solutions
- Focus on stylistic preferences rather than substantive issues
- Miss context that the proposal author has
Treat every opinion as a hypothesis to evaluate, not a directive to follow.
2. Focus on the Problem, Not the Authority
Evaluate feedback based on:
- Is the underlying concern valid? (separate the problem from the proposed solution)
- Does the reviewer provide concrete reasoning? (opinions without reasons need clarification)
- Is the feedback actionable and specific? (vague "this feels wrong" needs to be unpacked)
- Does it conflict with stated requirements or constraints the reviewer may not know about?
Do NOT evaluate feedback based on:
- Who said it (seniority doesn't make an opinion correct)
- How strongly it was worded (emphasis doesn't equal correctness)
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 · 220 lines · 198 tokens per session scan A 99e6e4ebec4b
review-regression is a skill published in the GitHub repository gongxuanzhang/shengsheng-skill (10 stars, last pushed 2mo ago), licensed MIT. It adds 198 tokens to every session and 2,436 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…