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 ArcBlock/agent-skills --skill issue-sweep-batchgit clone --depth 1 https://github.com/ArcBlock/agent-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/arcblock/agent-skills/issue-sweep-batch)<a href="https://agentmods.dev/skills/arcblock/agent-skills/issue-sweep-batch"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/issue-sweep-batch/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/arcblock/agent-skills/issue-sweep-batch"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/issue-sweep-batch.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 | $0.00060 | $0.03939 |
| Opus 5.5 | $0.00024 | $0.01576 |
| Sonnet 5.5 | $0.00012 | $0.00788 |
| Haiku 4.5 | $0.00006 | $0.00394 |
Grade A, and why
issue-sweep-batch 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 9d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
issue-sweep-batch — 把 epic 的形成做成一步
Repo profile — 先读
.claude/repo-profile.md。 本 skill 与仓库无关； arc 是参考实现。repo_slug、label 集合、树的划分都从 profile 取，别硬编码。
它在哪一层
issue-sweep 逐条处理「人回复了的」issue per-issue triage
issue-sweep-batch 把一堆无人认领的 issue 聚成可派 epic ← 本 skill
epic-conductor 把一个已定义的 epic 推到合并 per-epic execution
/agentloop:issue-sweep 的候选集主动排除 epic-managed / epic:<n>——它明确不管
已归 epic 的东西。/agentloop:epic-conductor 的 Step 1 是 Decompose——它假设 epic 已存在。
中间这层此前没有 skill 负责。
只产出 epic，不碰任何既有机制
- 不派工、不合并、不修改既有 epic 的成员、不动任何 issue 的状态标签
- 唯一的写操作是：建新 epic issue + 给候选挂
epic:<新号>+ 写 ledger - 因此它是纯增量的：不跑它，工厂的行为和今天完全一样
它其实是全局分类器，epic 只是一种输出
真正在做的事是：给存量里每一条工作项确定它属于哪一类、在那类的哪一簇， 并知道这个结论什么时候失效。 epic 是「一簇 bug 且路径面不相交」时的产物，不是全部。
分类轴按类型不同（不可混用）
| 类型 | 轴 | 聚簇判据 |
|---|---|---|
bug |
defectLayer |
这几条能不能被同一个修复方向覆盖？ |
feature / idea |
capabilityArea |
这几条会不会被同一次设计决定一起决定掉？ |
research |
openQuestion |
这几条会不会被同一次调查一起回答？ |
symptom |
openQuestion |
这几条会不会被同一次诊断一起回答？ |
untyped |
无轴 | 必须先定类型，不能硬分 |
When classifying a symptom, or when an item has no type label, read reference/symptom.md.
三种模式
--types bug,untyped # work-object 默认（导入无 keywords → untyped）；`--types bug` 仍只扫 bug
--mode new # 只处理**从未分类**的 —— 反复归类没动的东西是纯浪费
--mode revalidate # 只重验**已分类**的 —— 世界变了之后旧结论还成立吗
--mode all # 两者（默认）
When running --mode revalidate, or when a classification can expire because a neighbor changed, read reference/invalidation.md.
工厂健康
页面顶部与 CLI 首行：🔴 ACTION REQUIRED / 🟡 DEGRADED / 🟢 HEALTHY。硬 detector 在 health.ts，assess 合成至多三条解释。agent 读 --json，不读截图。
门槛住在 health.ts 的 T。When changing them, read reference/health.md.
可视化：--html
bun .../sweep-batch.ts --dry-run --html sweep.html && open sweep.html
What ships with it
30 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.
- reference/health.md 3.1 KB
- reference/html.md 7.4 KB
- reference/invalidation.md 1.5 KB
- reference/source-roots.md 1.9 KB
- reference/source.md 2.5 KB
- reference/symptom.md 2.7 KB
- scripts/classify.test.ts 17 KB runs code
- scripts/classify.ts 13 KB runs code
- scripts/fixtures/all-zero.ts 1016 B runs code
- scripts/fixtures/empty.ts 251 B runs code
- scripts/fixtures/full.ts 1.6 KB runs code
- scripts/fixtures/lib.ts 2.6 KB runs code
- scripts/fixtures/single-bin.ts 1.2 KB runs code
- scripts/fixtures/uncollected.ts 1.1 KB runs code
- scripts/health.test.ts 19 KB runs code
- scripts/health.ts 15 KB runs code
- scripts/html.test.ts 12 KB runs code
- scripts/html.ts 41 KB runs code
- scripts/lib.test.ts 12 KB runs code
- scripts/lib.ts 11 KB runs code
- scripts/source.conformance.test.ts 8.5 KB runs code
- scripts/source.ts 42 KB runs code
- scripts/source.work-object.test.ts 62 KB runs code
- scripts/stats.test.ts 9.3 KB runs code
- scripts/stats.ts 7.0 KB runs code
- scripts/sweep-batch.ts 31 KB runs code
- scripts/typing.test.ts 10 KB runs code
- scripts/typing.ts 9.7 KB runs code
- scripts/ui-verify.mjs 20 KB runs code
- scripts/ui-verify.test.ts 2.6 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.
- 9d ago Changed · -4 lines ad67bf3a9dd3
- 20d ago Changed · -259 lines · -103 tokens per session b8a4c41eb98b
- 1mo ago Changed · +9 lines 407fca198df2
- 1mo ago First seen · 509 lines · 163 tokens per session scan A 5ed7479f447e
issue-sweep-batch is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 60 tokens to every session and 3,939 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.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.