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/issue-triagenpx skills add 10CG/Aria --skill issue-triagegit 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/issue-triage)<a href="https://agentmods.dev/skills/10cg/aria/issue-triage"><img src="https://agentmods.dev/badge/skills/10cg/aria/issue-triage.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 | $0.00103 | $0.03752 |
| Opus 5 | $0.00051 | $0.01876 |
| Sonnet 5 | $0.00021 | $0.00750 |
| Haiku 4.5 | $0.00010 | $0.00375 |
Grade A, and why
issue-triage 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 4d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Triage (issue-triage v1.0)
版本: 1.0.0 | 角色: issue 接收方核对 十步循环角色: B.2 实施阶段 — 接收 issue 后的前置核对步骤，防止在过期信息或未复现 bug 上开起新的 cycle 机械化: Step 0 由
scripts/triage.py(stdlib-only Python) 产出 JSON snapshot，AI 读 snapshot 进行 Step 6 复现 + verdict 综合。
快速开始
我应该使用这个 Skill 吗？
使用场景:
- 收到 issue 后，在起新 OpenSpec / branch 之前
- 确认 bug 是否在当前版本可复现
- 查看是否已有 in-flight PR 或本地分支处理同一问题
- 需要留 audit trail (verdict comment) 的 issue 核对
不使用场景:
- 已完成 triage、正在起修复 cycle → 直接
/phase-a-planner - 只是看 issue 列表 / 查进度 →
/state-scanner - 向 Aria 维护团队报告问题 →
/aria-report(方向相反，见 §与 aria-report 的关系)
核心功能
| 阶段 | 内容 | 机械化 |
|---|---|---|
| Step 0 | 执行 triage.py，产出 triage-report.json |
全自动 (triage.py) |
| Steps 1-5 | 读取 issue、版本核对、代码路径验证、git 历史、in-flight 检查 | 全自动 (collectors) |
| Step 6 | Reproduction — 三模式 exit (auto / pause / skip) | AI 辅助 |
| 综合输出 | Verdict 计算 + severity / recommended_action 填写 + triage-comment.md 草稿 |
AI |
步骤定义 (SOT):
6 步流程的完整定义（每步目的、检查项、输出字段、失败模式）见 standards/conventions/issue-triage.md §Steps。本文档不复制步骤定义，仅描述 Skill 调用契约。
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 |
|---|---|---|
issue_triage.default_repo |
"" (从 forgejo_config 推断) |
裸编号时的默认仓库 |
issue_triage.repro_timeout_seconds |
120 |
Step 6 单次复现命令超时 |
issue_triage.step6_mode |
"auto" |
默认 Step 6 模式: auto / pause / skip |
issue_triage.output_dir |
".aria" |
triage-report.json 输出目录 |
执行流程
Step 0: 机械执行 triage.py (硬约束)
不可协商: Steps 1-5 所有字段由
scripts/triage.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/issue-triage/scripts/triage.py" \
--issue "<owner>/<repo>#N" \
--output .aria/triage-report.json
退出码契约:
| 退出码 | 含义 | AI 动作 |
|---|---|---|
0 |
全部成功 (steps_with_data == 5) |
读 .aria/triage-report.json，进入 Stage 2 |
10 |
部分 collector 错误 (steps_with_data >= 2 AND <= 4)，report 仍可用 |
读 report，展示受影响步骤 warning，继续 Stage 2 |
30 |
硬失败 (steps_with_data < 2)，不生成 report |
Abort，展示 stderr，提示检查凭证和 issue 引用；禁止进入 Step 6 |
What ships with it
27 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.
- evals/evals.json 2.1 KB
- references/triage-report-schema.md 9.6 KB
- references/triage-report.schema.json 12 KB
- scripts/collectors/__init__.py 1001 B runs code
- scripts/collectors/_code.py 8.9 KB runs code
- scripts/collectors/_common.py 1.7 KB runs code
- scripts/collectors/_history.py 5.4 KB runs code
- scripts/collectors/_inflight.py 9.1 KB runs code
- scripts/collectors/_issue.py 5.5 KB runs code
- scripts/collectors/_version.py 8.2 KB runs code
- scripts/triage.py 12 KB runs code
- tests/__init__.py 0 B runs code
- tests/conftest.py 8.7 KB runs code
- tests/fixtures/forgejo/issue-101.json 1.3 KB
- tests/fixtures/forgejo/issue-not-found.json 112 B
- tests/fixtures/issue-bodies/backtick-citation.md 169 B
- tests/fixtures/issue-bodies/md-link-citation.md 248 B
- tests/fixtures/issue-bodies/no-citation.md 247 B
- tests/fixtures/issue-bodies/prose-citation.md 156 B
- tests/test_collectors_code.py 11 KB runs code
- tests/test_collectors_history.py 8.5 KB runs code
- tests/test_collectors_inflight.py 13 KB runs code
- tests/test_collectors_version.py 9.6 KB runs code
- tests/test_exit_codes.py 8.4 KB runs code
- tests/test_idempotency.py 6.2 KB runs code
- tests/test_schema.py 10 KB runs code
- tests/test_secret_hygiene.py 9.9 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.
- 4d ago First seen · 311 lines · 103 tokens per session scan A dd6f92dce4af
issue-triage is a skill published in the GitHub repository 10CG/Aria (2 stars, last pushed 5d ago), licensed MIT. It adds 103 tokens to every session and 3,752 once invoked, about $0.0005 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
extracting-requirements
Use when starting an iterative-development run on human spec collateral — reads the spec, produces per-epic requirement files with proof obligations and behavior scenario cards with stable IDs.
iterative-development
Use when implementing a project with a large, comprehensive, or ambiguous spec — extracts requirements with proof obligations, defines a walking skeleton with its first journey scenario, then loops through audited sprints that continuously build a behavior evidence corpus. Completion means passing evidence, not just…
scoping-the-simplest-core
Use when turning extracted requirements into a roadmap — selects the walking skeleton iteration with its first journey scenario, orders remaining work into follow-on iterations, and applies story splitting when ACs have different dependency profiles.
running-an-iteration
Use when executing the next pending iteration from an iterative-development roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches implementing-tasks, runs impacted + sentinel scenarios, and updates artifacts.
auditing-progress
Use when an iteration has just finished and you need to verify behavior evidence quality in three tiers — deep evidence for current stories, impacted behavior for touched scenarios, and sentinel corpus for high-value regression detection.
implementing-tasks
Use when executing a batch of TDD-sized tasks inside a running-an-iteration call — dispatches an implementer subagent per task following red-green-refactor discipline and returns per-task completion status.