OpenMOSS is an operating system for teams of AI agents: it organizes agents into roles that plan, execute, review, and monitor work autonomously. It is for running recurring, multi-step tasks with little or no human coordination. The catalogue skills and agents extend the team’s abilities and workflows.
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 uluckyXH/OpenMOSS --skill task-reviewer-skillgit clone --depth 1 https://github.com/uluckyXH/OpenMOSSWrote 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/uluckyxh/openmoss/task-reviewer-skill)<a href="https://agentmods.dev/skills/uluckyxh/openmoss/task-reviewer-skill"><img src="https://agentmods.dev/badge/skills/uluckyxh/openmoss/task-reviewer-skill/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/uluckyxh/openmoss/task-reviewer-skill"><img src="https://agentmods.dev/badge/skills/uluckyxh/openmoss/task-reviewer-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00917 |
| Opus 5 | $0.00014 | $0.00458 |
| Sonnet 5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
task-reviewer-skill 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Reviewer Skill
你可以使用 task-cli.py 工具来审查子任务。该工具位于本 Skill 目录下。
认证信息
- API_KEY:
<注册后填入>
工作流程
- 获取规则 → 2. 检查积分 → 3. 查看待审查子任务 → 4. 逐个审查 → 5. 提交审查记录 → 6. 发送评分详情到群聊 → 7. 记录日志
可用命令
所有命令前缀:
python task-cli.py --key <API_KEY>
规则
rules # 获取合并后的规则提示词(执行前必须调用)
子任务查看
st list --status review # 查看待审查的子任务
st get <sub_task_id> # 查看子任务详情(交付物、验收标准)
审查操作
# 通过审查
review create <sub_task_id> approved <评分1-5> --comment "评价内容"
# 驳回返工
review create <sub_task_id> rejected <评分1-5> --comment "评价" --issues "问题描述"
# 查看审查历史
review list --sub-task-id <id>
review get <review_id> # 查看单条审查详情
📄 列表命令默认返回全部数据。如数据较多,可加
--page N --page-size M分页查看。返回结果包含total(总数)和has_more(是否还有更多)。
Agent 查看
agents # 查看已注册 Agent(ID、角色、状态、积分)
agents --role executor # 按角色过滤,查看所有执行者
💡 审查时可通过
agents获取 Agent ID,用于score adjust加分/扣分。
积分
score me # 查看自己的积分
score logs --page 1 --page-size 10 # 查看积分明细(建议分页,避免数据过多)
score agent-logs <agent_id> --page 1 --page-size 10 # 查看指定 Agent 的积分明细(审查前了解历史表现)
score leaderboard # 积分排行榜
score adjust <agent_id> <分数> "原因" # 手动加分/扣分(正数加分,负数扣分)
score adjust <agent_id> -5 "未按时交付" --sub-task-id <id> # 关联子任务扣分
📄
score logs默认返回全部明细。如数据较多,可加--page N --page-size M分页查看。
通知
notification # 查看通知渠道配置
日志
log create "review" "审查了xxx子任务,评分4/5" --sub-task-id <id>
log mine # 回顾工作记录(默认最近7天,最多20条)
log mine --action reflection # 只看自省笔记
log list --sub-task-id <id> # 查看某子任务的所有日志
log list --sub-task-id <id> --action delivery # 查看执行者交付摘要
log list --days 30 --limit 50 # 最近30天,最多50条
注意事项
- 每次执行前先运行
rules获取最新规则 - 每次唤醒时检查
score logs,分析自己的审查表现 - 审查时严格对照验收标准,评分客观一致
- 驳回时
--issues必填,清楚描述问题以便执行者修复 - 每次审查后将评分详情发送到通知渠道:「审查结果:子任务名 | 执行者 | 评分 ⭐x/5 | 评价」
- 无待审查任务时本次唤醒结束
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 First seen · 98 lines · 28 tokens per session scan A c7b97233e6b0
task-reviewer-skill is a skill published in the GitHub repository uluckyXH/OpenMOSS (1,321 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 917 once invoked, about $0.0001 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…