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 agentmods add skills/10cg/aria/state-scannernpx skills add 10CG/Aria --skill state-scannergit clone --depth 1 https://github.com/10CG/AriaWrote 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/state-scanner)<a href="https://agentmods.dev/skills/10cg/aria/state-scanner"><img src="https://agentmods.dev/badge/skills/10cg/aria/state-scanner.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.06933 |
| Opus 5 | $0.00030 | $0.03467 |
| Sonnet 5 | $0.00012 | $0.01387 |
| Haiku 4.5 | $0.00006 | $0.00693 |
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 3d 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 — 380 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 v3.0)
版本: 3.0.0 | 角色: 十步循环统一入口 机械化: v3.0.0 起 Phase 1.x 由
scripts/scan.py(stdlib-only Python) 机械产出 JSON snapshot, AI 读 snapshot 进入阶段 2 推荐。v2.x prose 路径保留mechanical_mode=falseopt-out, 计划下一 minor (v1.19.0+) 移除 (AD-SSME-5;v1.18.0 ship 时仍保留 — 监测使用量后决定)。
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、自定义检查、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 |
state_scanner.mechanical_mode |
true |
v3.0.0+: true 走 scan.py 路径, false 回退 v2.x prose 路径 (计划 v1.19.0+ 移除, v1.18.0 ship 时仍保留) |
state_scanner.issue_scan.platform_hostnames.forgejo |
["forgejo.10cg.pub"] |
v1.30.0+: Forgejo hosts 可通过 ARIA_FORGEJO_HOSTS env var (comma-separated) 覆盖, 优先级 env > config > default; 同时影响 forgejo_config 和 issue_scan 两 collector (per OpenSpec aria-forgejo-hosts-parameterization) |
workflow.auto_proceed |
false |
Phase 间自动推进 |
执行流程
Step 0: 机械执行 scan.py (v3.0.0 硬约束)
不可协商: Phase 1 所有字段由
scripts/scan.py机械采集, AI 不得跳过 / 不得逐字段手工 Bash 替代 / 不得在失败时"降级"到手工采集。
执行命令:
python3 "${CLAUDE_PLUGIN_ROOT:-aria}/skills/state-scanner/scripts/scan.py" \
--output .aria/state-snapshot.json
退出码契约 (详见 state-snapshot-schema.md §Exit code consumer contract):
What ships with it
60 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.
- docs/coordination-ref-schema.md 11 KB
- docs/rule9-5layer-matrix.md 15 KB
- lib/__init__.py 4.2 KB runs code
- lib/claim_lifecycle.py 17 KB runs code
- lib/claim_schema.py 13 KB runs code
- lib/collision.py 14 KB runs code
- lib/concurrent_tracks.py 8.0 KB runs code
- lib/constants.py 4.3 KB runs code
- lib/coordination_ref.py 50 KB runs code
- lib/failure_handlers.py 25 KB runs code
- lib/gc.py 18 KB runs code
- lib/identity.py 8.8 KB runs code
- lib/reconcile.py 15 KB runs code
- lib/track_id.py 6.6 KB runs code
- lib/worktree_manager.py 42 KB runs code
- RECOMMENDATION_RULES.md 12 KB
- references/confidence-scoring.md 5.8 KB
- references/cross-platform-commands.md 3.5 KB
- references/interrupt-recovery.md 9.7 KB
- references/issue-scanning.md 47 KB
- references/json-diff-normalizer.md 12 KB
- references/layer-l-integration.md 5.4 KB
- references/migration-v1-to-v2.md 478 B
- references/migration-v2.9-to-v3.0.md 8.7 KB
- references/output-formats.md 29 KB
- references/phase-1-collectors.md 9.8 KB
- references/predicate-domain-table.md 7.2 KB
- references/recommendation-stages.md 8.0 KB
- references/rules/advanced-rules.md 26 KB
- references/rules/basic-rules.md 20 KB
- references/rules/operations.md 10.0 KB
- references/runtime-probe-declaration.md 9.2 KB
- references/state-snapshot-schema.md 69 KB
- references/status-field-guide.md 4.0 KB
- references/sync-detection.md 25 KB
- scripts/collectors/__init__.py 2.2 KB runs code
- scripts/collectors/_common.py 26 KB runs code
- scripts/collectors/_status.py 9.7 KB runs code
- scripts/collectors/architecture.py 3.1 KB runs code
- scripts/collectors/audit.py 1.9 KB runs code
- scripts/collectors/changes.py 2.7 KB runs code
- scripts/collectors/coordination_fetch.py 13 KB runs code
- scripts/collectors/custom_checks.py 16 KB runs code
- scripts/collectors/forgejo_config.py 6.3 KB runs code
- scripts/collectors/git.py 13 KB runs code
- scripts/collectors/handoff_multibranch.py 20 KB runs code
- scripts/collectors/handoff_worktrees.py 17 KB runs code
- scripts/collectors/handoff.py 21 KB runs code
- scripts/collectors/interrupt.py 1.8 KB runs code
- scripts/collectors/issue_scan.py 33 KB runs code
- scripts/collectors/multi_remote.py 69 KB runs code
- scripts/collectors/openspec.py 15 KB runs code
- scripts/collectors/readme.py 2.2 KB runs code
- scripts/collectors/remote_refresh.py 32 KB runs code
- scripts/collectors/requirements.py 7.0 KB runs code
- scripts/collectors/standards.py 975 B runs code
- scripts/collectors/sync.py 26 KB runs code
- scripts/collectors/upm.py 14 KB runs code
- scripts/coordination_probe.py 11 KB runs code
- scripts/issue_cache_freshness_probe.py 7.5 KB runs code
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.
- 3d ago First seen · 380 lines · 61 tokens per session scan A 7d2a38ffa323
state-scanner is a skill published in the GitHub repository 10CG/Aria (2 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 6,933 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
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
requirement-forge-refiner
Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming conventions. Produces a formal requirement-standards.md that the requirement-quality atom reads via config resolution…
glab
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
pilot
One autonomous Pilot cycle - fetch the agenda, execute the top item, journal, exit. Injected by the terminal host - not for manual invocation loops.
status
Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.