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 hxy91819/mason-skills --skill project-stagegit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/project-stage)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/project-stage"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/project-stage/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/hxy91819/mason-skills/project-stage"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/project-stage.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 | $0.00066 | $0.00861 |
| Opus 5 | $0.00033 | $0.00430 |
| Sonnet 5 | $0.00013 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
project-stage 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Stage
Agents default to treating every repository as a live system with unknown callers, old deployed versions, and persisted data to migrate. That default is right for production and wrong for experiments, where it silently piles up fallbacks, shims, optional parameters, and "v2" paths that nobody consumes. The fix is not a global "be simple" instruction; it is a short, factual declaration in the repository itself of who consumes this code.
Procedure
This skill runs only on explicit $project-stage invocation. It edits the repository's
instruction file, so a passing mention of "this is experimental" must not trigger it.
- Locate the repository's agent instruction file:
AGENTS.md,CLAUDE.md, or whatever the project already uses. CreateAGENTS.mdat the repo root if none exists. - If the file already has a
## 项目阶段section, update it instead of adding a second. - Decide the stage. The user usually knows; if the prompt already says "experimental", "prototype", "线上", "已发布" or similar, do not ask. Ask a single question only when the stage is genuinely unstated and cannot be inferred from the repo (no deploy config, no migrations, no published package usually means experimental).
- Insert the matching template below near the top of the file. Fill in the bracketed facts for production; leave the experimental template as is unless a fact is wrong.
- Tell the user which file was edited and which stage was declared. Do not touch any other file.
The declaration lists facts, not attitudes. "No deployed old version exists" removes the reason for a compatibility branch; "keep it simple" only discounts it.
Template: 实验期
## 项目阶段:实验期
- 唯一消费者是本仓库内的代码。没有外部调用方,没有已部署的旧版本,没有需要迁移的持久化数据。
- 破坏性修改是免费的:直接改签名、改数据格式、删代码、重建 schema。不写 deprecate 路径、不留 fallback、不加 v2 并存。
- 不为"未来可能"预留:不加没人传的可选参数、没人读的配置项、只有一个实现的抽象层。需要时再加。
- 审查时对每个 fallback 分支、兼容 shim、可选参数问同一个问题:它服务于哪个真实存在的消费者?答不出就删。
- 项目上线时把本节改为「线上期」并列出真实消费者。
Template: 线上期
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +2 lines 47fee91984d0
- 5d ago First seen · 64 lines · 66 tokens per session scan A f3ceb3467b4f
project-stage is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 861 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 2026-09-07.
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…