Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/10CG/Arianpx agentmods add skills/10cg/aria/skill-snapshot-v2.4.0Wrote 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/10cg/aria/skill-snapshot-v2.4.0)<a href="https://agentmods.dev/skills/10cg/aria/skill-snapshot-v2.4.0"><img src="https://agentmods.dev/badge/skills/10cg/aria/skill-snapshot-v2.4.0/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/10cg/aria/skill-snapshot-v2.4.0"><img src="https://agentmods.dev/badge/skills/10cg/aria/skill-snapshot-v2.4.0.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 | $0.00061 | $0.06408 |
| Opus 5 | $0.00030 | $0.03204 |
| Sonnet 5 | $0.00012 | $0.01282 |
| Haiku 4.5 | $0.00006 | $0.00641 |
Grade A, and why
state-scanner 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 10d 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 — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
状态扫描与智能推荐 (State Scanner v2.7)
版本: 2.7.0 | 角色: 十步循环统一入口
快速开始
我应该使用这个 Skill 吗？
使用场景:
- 开始任何开发任务前的状态检查
- 不确定应该使用哪个工作流
- 需要系统推荐最佳执行路径
- 查询多模块项目的整体进度
不使用场景:
- 已知要执行特定 Phase → 直接调用 Phase Skill
- 只想运行特定步骤 → 直接调用步骤 Skill
核心功能
| 功能 | 描述 |
|---|---|
| 状态感知 | 收集 Git 状态、UPM 进度、OpenSpec 状态、审计状态、变更分析 |
| 智能推荐 | 基于状态生成工作流推荐，附带理由说明 |
| 用户确认 | 展示选项，让用户确认或自定义工作流 |
| 工作流启动 | 将确认的工作流传递给 workflow-runner 执行 |
配置 (config-loader)
执行前读取 .aria/config.json，缺失则使用默认值。参见 config-loader。
| 字段 | 默认值 | 说明 |
|---|---|---|
state_scanner.confidence_threshold |
90 |
置信度阈值 (0-100) |
state_scanner.auto_execute_enabled |
false |
高置信度自动执行 |
state_scanner.auto_execute_rules |
["commit_only", "quick_fix", "doc_only"] |
允许自动执行的规则 |
state_scanner.audit_log_path |
".aria/audit.log" |
审计日志路径 |
workflow.auto_proceed |
false |
Phase 间自动推进 |
执行流程
阶段 0: 中断检测 (Pre-flight)
详细逻辑见 interrupt-recovery.md | 状态格式见 workflow-state-schema.md
检查 .aria/workflow-state.json — 不存在或损坏则跳过进入阶段 1 (损坏时备份并警告)。若 status=in_progress|suspended: (1) 验证 git_anchor.branch 匹配当前分支，不匹配仅 Abandon/Inspect; (2) 若 session.last_active_at<5min 且 session_id 不同，警告并发冲突; (3) 展示 [1]Resume [2]Abandon [3]Inspect — Resume→workflow-runner(resume=true)，Abandon→删除状态进入阶段1，Inspect→详情后重选。若 status=failed: 显示失败上下文，提供 [1]Retry [2]Abandon [3]Inspect。
阶段 1: 状态收集
收集内容:
git:
current_branch: 当前分支名
uncommitted_changes: 未提交的变更数
staged_files: 已暂存文件列表
unstaged_files: 未暂存文件列表
recent_commits: 最近 5 条提交
project:
phase_cycle: 从 UPM 读取当前 Phase/Cycle
active_module: 活跃模块 (mobile/backend/shared)
openspec_status: OpenSpec 变更状态
changes:
file_types: 变更文件类型分类 (code/test/docs/config)
change_count: 变更文件数量
complexity: 变更复杂度评估 (Level1/Level2/Level3)
architecture_impact: 是否影响架构文档
test_coverage: 是否有对应测试文件
skill_changes: # v1.7.0 新增: Skill 变更检测
detected: 是否有 SKILL.md 变更
modified_skills: 变更的 Skill 列表
ab_status: # 各 Skill 的 AB 验证状态
verified: 有新鲜 AB 结果的 Skill 列表
needs_benchmark: 缺少 AB 结果的 Skill 列表
audit: # 新增: 审计状态
enabled: true/false # audit.enabled 配置值
mode: adaptive/convergence/challenge/manual # audit.mode 配置值
active_checkpoints: # 启用的检查点列表 (非 "off" 的)
- post_spec
- post_implementation
- pre_merge
last_audit: # 最近一次审计报告 (如有)
checkpoint: post_spec # 检查点名称
timestamp: "2026-03-27T10:00:00Z"
verdict: PASS/PASS_WITH_WARNINGS/FAIL
converged: true/false
requirements: # 新增: 需求状态
configured: 是否配置需求追踪
prd_exists: PRD 文件是否存在
stories:
total: User Story 总数
ready: 就绪待实现
in_progress: 进行中
done: 已完成
coverage:
with_openspec: 有技术方案的 Story 数
without_openspec: 无技术方案的 Story 数
forgejo:
synced: 是否与 Forgejo 同步
drift: 是否有状态偏差
What ships with it
6 files 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.
- 10d ago First seen · 691 lines · 61 tokens per session scan A 201f1e567cbf
state-scanner is a skill published in the GitHub repository 10CG/Aria (2 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 6,408 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 2026-08-31.
Other skills, from other repositories
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
continue
Autonomous work — find and execute ready tasks.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.
debt
A command for showing and closing unanswered questions attached to project documents such as requirements, specifications, features, and designs. It can show questions for the whole project or for one document.
pr
A command for managing pull requests on GitHub or Bitbucket Server. A pull request is a request for other developers to review and merge changes into a project branch.
shipyard-executing-plans
Use when you have a written implementation plan to execute, either in the current session with builder/reviewer agents or in a separate session with review checkpoints. Also use when the user says "build this", "implement this", "execute the plan", "run the plan", or when a plan file has been loaded with independent…