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 zuoyebang/aiweave --skill concurrency-reviewgit clone --depth 1 https://github.com/zuoyebang/aiweaveWrote 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/zuoyebang/aiweave/concurrency-review)<a href="https://agentmods.dev/skills/zuoyebang/aiweave/concurrency-review"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/concurrency-review/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/zuoyebang/aiweave/concurrency-review"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/concurrency-review.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 | $0.00100 | $0.02186 |
| Opus 5 | $0.00050 | $0.01093 |
| Sonnet 5 | $0.00020 | $0.00437 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
concurrency-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
审计代码的并发安全性。范围:$ARGUMENTS(空则审计 git diff main..HEAD)。
公共步骤模板见 skills-spec/01_skill_authoring_guide.md §A-§E。本 Skill 不生成代码,故第 5 步测试同步不适用。
本 Skill 是 新增的审计类 Skill。"代码 ↔ 约束"一致性审计,与
doc-sync-check(代码 ↔ 文档一致性)互补不替代。
第 0 步:🚫 模块 + 启用状态检查
- 读
BUILD_STATUS.md§0 —— 命中 🚫 模块的文件跳过审计(不报问题) - 读
INDEX.md§0 AIWeave 采纳进度 —— 如docs-spec/20_concurrency_safety标 ⬜ 未启用 → 跳过本 Skill,提示"本工程未启用 20,跳过 concurrency-review"
第 1 步:读取约束源
读以下文件(按顺序):
docs/architecture/concurrency_safety.md—— §2 共享状态注册表 + §3 锁策略 + §4 channel 清单 + §6 危险操作清单docs/architecture/ai_dev_guide.md§10.1 —— grep 锚 rule-id 索引(R-CONC-*)docs/BUILD_STATUS.md§11 —— 约束清单状态轨道(确认哪些 rule-id 启用)
第 2 步:扫描代码范围
按 $ARGUMENTS 确定扫描范围:
- 空:
git diff main..HEAD --name-only取新增/修改的 .go 文件 - 文件路径:直接以该路径为范围
- service 模块:
service/{module}/**/*.go
第 3 步:10 项 grep 锚检查
grep 锚定位为"信号级"非"判定级"。所有命中标 🟡 待复核;最终判定由人工 reviewer 决定是否阻断合并。
检查 R-CONC-LOCK-IO:锁内做网络 IO
grep 模式:'\.Lock\(\)[\s\S]{0,500}?(http\.|Mysql|Redis|tlog\.)'
误报排除:
- RLock 中读小对象
- 同步只读类操作(如 Redis GET 单次 < 1ms 的情况)
- 行末含 // aiweave:allow=R-CONC-LOCK-IO 注解
检查 R-CONC-LOCK-LOG:锁内打日志
grep 模式:'\.Lock\(\)[\s\S]{0,300}?(tlog\.|log\.)'
误报排除:
- 异常路径的关键日志(不可避免)
- 行末含 // aiweave:allow=R-CONC-LOCK-LOG 注解
检查 R-CONC-MAP-RACE:map 并发写
判定:文件含 `var .* map\[` 且同文件存在 `go func` 且未引用 sync.RWMutex / sync.Map
误报排除:
- 局部 map 不跨 goroutine
- main / init 中只读 map(启动后只读)
- 行末含 // aiweave:allow=R-CONC-MAP-RACE 注解
检查 R-CONC-DOUBLE-CLOSE:关闭已关闭的 channel
判定:`close\([^)]+\)` 同一 channel 在文件内出现多次且无 sync.Once 保护
误报排除:
- 单一所有者 close 模式
- 行末含 // aiweave:allow=R-CONC-DOUBLE-CLOSE 注解
检查 R-CONC-SEND-CLOSED:向已关闭的 channel 发送
判定:`<-` channel 关闭后仍有 send 路径(静态分析判定,准确率较低 → 优先标 🟡)
检查 R-RESOURCE-DEFER-LOOP:defer 在 for 循环内
grep 模式:'for [^{]*\{[\s\S]{0,300}?defer '
误报排除:
- 循环体内显式调用 Close 而非 defer
- 循环次数 ≤ {Loop-defer-safe}(如 < 10,影响小)
- 行末含 // aiweave:allow=R-RESOURCE-DEFER-LOOP 注解
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.
- 12d ago First seen · 171 lines · 100 tokens per session scan A 29af553583e9
concurrency-review is a skill published in the GitHub repository zuoyebang/aiweave (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,186 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 2026-08-30.
Other skills, from other repositories
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
antidote
Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+ lines without deleting code.
pr-feedback-ingest
Turn PR feedback (Greptile, CI, bots, humans) into a structured traceable backlog aligned with TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md so the next execution step can be a narrow implement-approved-slice or a small planning touch without losing alignment. Corrective scope only. Use when a PR is open or…
repo-consistency-sweep
Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability…
review-hard
Review the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Surfaces meaningful issues (not cosmetic feedback); not a replacement for external review systems. Returns no-op when the review would not materially…
verify-against-rubric-fleet
Orchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric. Dispatches N stateless Sonnet sub-agents in parallel; each receives ONE artifact + the SAME rubric + read-only tools (no TASKSTATE, no DECISIONS, no prior history); returns structured per-criterion verdict.…