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 skill-authoring-gategit 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/skill-authoring-gate)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/skill-authoring-gate"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/skill-authoring-gate/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/skill-authoring-gate"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/skill-authoring-gate.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 | $0.00039 | $0.02765 |
| Opus 5.5 | $0.00016 | $0.01106 |
| Sonnet 5.5 | $0.00008 | $0.00553 |
| Haiku 4.5 | $0.00004 | $0.00277 |
Grade A, and why
skill-authoring-gate 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 22d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 编写门禁
按实际使用上下文决定手动还是自动。用户的维护偏好是：新技能默认手动，只有确实需要 Agent 自行发现的入口才自动。这覆盖 skill-creator 的通用自动默认值；不因宿主省略配置时默认为 true，就省略本仓的策略选择。
编辑前
- 加载
$writing-for-agents；涉及调用策略或 router 时按该 Skill 的指引读取SKILL-MECHANICS.md。 - 加载
$skill-creator，按用户偏好和本门禁选择调用方式，其余结构指导仍适用。 - 读取目标 Skill、已有 metadata 及调用清单，检查真实使用请求、调用方和自动发现的必要性。窄修改只检查相关路径。
编写与审查共用原则
编写时用以下原则组织指令，审查时用同一标准检查现有内容；窄修改只检查受影响的规则及其引用。
- 精确触发：description 用简短能力说明加具体触发条件，排除容易混淆的相邻任务，检查相关技能是否抢占同一请求。是否触发的判断（含不触发的情形）只写在 description，正文要触发后才加载；实现方式、参数、长能力清单和执行步骤放正文；未改变匹配范围时保留原描述。
- 按需加载：正文保留共同目标、必要约束和分支入口；较长的分支细节放支持文档，并写明读取条件。依赖技能和文档按当前任务需要加载；简单技能保持单文件，不为拆分而增加 router。
- 保留有用指令：写明模型无法从环境直接得知的约定、真实易错点和决策依据。同一规则保留一个权威位置，其他位置引用；根据实际使用证据清理过时提醒，避免堆叠通用鼓励和重复要求。
- 按风险编排：开放任务写目标与判断标准；顺序影响正确性、权限或脆弱操作时才固定步骤。阅读范围和验证强度匹配改动及影响面，例如错字修正无需先读全库文档，共享逻辑变更仍需覆盖受影响路径。
- 明确边界与完成条件：说明可在已有授权内继续的工作、需人决策的条件，以及可检查的交付终点。若任务包含实现、运行、检查结果和修复失败，把它们计入完成条件，避免在第一版实现后提前结束；授权变更仍遵循下文规则。
- 考虑使用模型：共享技能按实际使用的模型评估指令价值。文章对 Astra 的观察可作为复查线索，不能单凭模型更强就删除验证、安全或授权约束；无法确认冗余时说明依据缺口。
按调用需求分类
| 上下文 | 策略与理由 |
|---|---|
| 人主动启动的独立流程，如规划、全库治理、发布、迁移编排 | 默认手动；由人决定何时进入这一套工作 |
| 当前任务中 Agent 必须自行选用的能力，如查 DB、TAPD 记录、日志或远端代码 | 可自动；以具体对象、平台和证据需求限定匹配 |
| 已启动流程必须自动衔接的下游 | 可自动；说明调用方、到达条件和完成边界，只覆盖该下游，不据此自动启动整套新流程 |
| 查询能力与独立编排混合 | 先区分入口；有实际查询自动需求时只自动匹配该分支，编排由人启动。无法清楚分流时保留手动，必要时按调用方式拆分 |
| 没有真实自动调用场景，或用途尚不清楚 | 保留手动，不因为模型能推断用途就开放发现 |
判断的关键是“谁需要在什么上下文找到它”，不是步骤多少、Skill 名称或是否含写入。DB/TAPD 查询即使包含鉴权、分页和重试，也仍是可供任务选用的能力。一个没有副作用的长篇规划流程，也可能只需要人手动启动。
选择自动时，在交付说明中记录至少一个真实正例、容易误选的相邻反例和自动选择的必要性；下游另说明实际调用方。任务未要求重新评估的既有策略保持不变，不顺手批量翻转。
本门禁保留自动发现：创建或修改 Skill 时需要自行加载这份编写约束；普通业务任务不触发，也不因已加载门禁就启动全库审计。
配置与正文一致
| 策略 | agents/openai.yaml |
SKILL.md frontmatter |
|---|---|---|
| 手动（新技能默认） | policy.allow_implicit_invocation: false |
disable-model-invocation: true；支持 Devin 时同步 triggers: [user] |
| 有明确需要的自动入口 | policy.allow_implicit_invocation: true |
移除禁用字段和仅限 user 的 triggers |
保留无关 UI/依赖字段，同步仓库调用清单。手动入口写明调用方式；自动入口仍可手动调用。手动流程启动后可使用所需能力，续办同一流程不要求用户每步重新输入命令；显式引用其他流程资料也不授权扩大任务。
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.
- 22d ago Changed 13e331c969d0
- 1mo ago Changed · +38 lines · +4 tokens per session 196a755d42fb
- 1mo ago Changed · +9 lines · +2 tokens per session 47fcf29c5093
- 1mo ago Changed · +24 lines · -32 tokens per session 989421d62de2
- 1mo ago Changed 40b46630bf2c
- 2mo ago Changed · +2 lines d63de0294a40
- 2mo ago First seen · 23 lines · 65 tokens per session scan A fd82632a7bb2
skill-authoring-gate is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,765 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
skill-authoring-gate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-authoring-gatehxy91819/mason-skills | Skill | 3 | today | MIT | A | 39 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |