Agent Browser
quran/quran.com-frontend-next
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。
Install Development Scheduler
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Ancienttwo/repo-harness development-scheduler --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/researches/development-scheduler/skill .claude/skills/development-scheduler && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .claude/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Ancienttwo/repo-harness development-scheduler --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/researches/development-scheduler/skill .agents/skills/development-scheduler && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .agents/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Ancienttwo/repo-harness development-scheduler --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/researches/development-scheduler/skill .cursor/skills/development-scheduler && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .cursor/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Ancienttwo/repo-harness.git --path docs/researches/development-scheduler/skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Ancienttwo/repo-harness development-scheduler --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/researches/development-scheduler/skill .gemini/skills/development-scheduler && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .gemini/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Ancienttwo/repo-harness development-schedulerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/researches/development-scheduler/skill .github/skills/development-scheduler && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .github/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ancienttwo/repo-harness --skill development-scheduler -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Ancienttwo/repo-harness development-scheduler --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/researches/development-scheduler/skill .opencode/skills/development-scheduler && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "development-scheduler" agent skill from https://github.com/Ancienttwo/repo-harness/tree/main/docs/researches/development-scheduler/skill into .opencode/skills/development-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "development-scheduler", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
development-scheduler- GitHub stars
- 434
- Token cost
- ~703 tokens
- SKILL.md length
- 172 words
- Files
- 3 (incl. references)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。
- Productivity & Automation work in your project
- SKILL.md covers 判断任务是否可派, 按事件跟进，按证据收敛 and 先保存证据，再清理
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Development Scheduler is an agent skill from Ancienttwo/repo-harness. 在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/hosts.md` and `references/repo-harness.md`).
It sits in Productivity & Automation. The repository describes itself as: File-backed workflow harness for reliable Claude Code and Codex sessions. The licence is MIT.
When your agent uses it
- Productivity & Automation work in your project
Example prompts
- “/development-scheduler”
What it can do on your machine
Read from SKILL.md and the folder at commit 3ea2f7b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Development Scheduler loads about 703 tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 28 tokens; SKILL.md has 172 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Ancienttwo/repo-harness at commit 3ea2f7b, republished under its MIT licence (© Ancienttwo). 172 words, ~703 tokens.
Download SKILL.mdSave it as
.claude/skills/development-scheduler/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- development-scheduler
- description
- 在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。
开发调度
Bot 负责用户对话、目标与验收、派工、监督和结果收集；worker 实现，独立 reviewer 审查。repo-harness session 可直接开发，Bot 模式复用 Host 既有 executor、远控和自动化。第一阶段以现有 task-agent、Herdr、Git 分支与 PR 状态为事实来源，引用原始返回和证据，不另建调度数据库或 Git common-dir runtime store。若将来出现真实并发或交接故障，再另开计划补最小锁。
Kanban 只读展示进度、阻碍、候选和证据；反馈、澄清、改需求、催办和审批跟进回 Bot，经受控工具执行。现有产品写入口尚未移除时，不能宣称 UI 已只读，也不能借 browser write 绕过边界。按需读 Host 接入与 repo-harness 适配。
判断任务是否可派
先读当前要求、项目规则和直接相关计划，确定目标、验收、读写范围、owner、依赖、预算与禁止动作。沿用已有授权直接推进；commit、push、merge、deploy、安装和清理分别受用户授权约束，Skill、建议、PASS 或上传成功都不授予权限。缺失资料或能力时阻塞依赖动作，能独立完成的部分继续，不能合成缺失身份或成功证据。
Herdr 基准版本为 0.9.3；控制前按安装版本读 herdr --skill、herdr --help 和相关命令组帮助，不裸启 Herdr 或用 mutating 命令探路。遵守真实 caller context；外部入口须有明确授权，不伪造 HERDR_ENV。核对目标 machine/server、cwd、live 身份和已有任务，采用返回 ID，不凭 UI 焦点、旧 pane ID 或 idle 判断可复用。真实 provider sessionID 与恢复位置来自可核验的 provider metadata/session 记录，pane、Tab、PID 不能代替它；未知身份阻塞相关派工和清理。
后端默认 Codex（gpt-6.1-sol，high），前端默认 Claude，具体任务限制优先。Claude 保留正常权限审批，不使用跳过权限模式；Claude 只读审查接入另立方案，当前独立审查使用已验证的 Codex 路径。启动任何 CLI worker 都必须复用 Pi 1.0 / OAR，通过现有 task-agent + Herdr 承载；不裸启 provider，不写手工 adapter/parser。安装版本未接通该路径时报告缺口并暂停启动，不以新 adapter 绕过。
按分支目标或独立写边界选择 worktree，避免微任务各建一个；Tab/pane 只是组织视图，不隔离文件。并行 writer 的文件 ownership 不重叠，共有文件交给唯一 owner 或顺序执行。冲突先停写并保存 WIP，前任确认停写后再交接，不能 stash、覆盖或终止他人工作。派工前核对同目标/角色/候选的未完成任务、已有结果和总预算，包含复用进程、descendants 与 reviewer 槽位；容量不足就排队，未知额度不能声称充裕。
按事件跟进，按证据收敛
给 worker 目标、冻结验收、输入来源、owner/读写范围、禁止动作、预算、结果位置和停止条件；记录足够定位任务、真实 session、候选及原始证据的引用，不逐任务抄登记字段表。提交成功不等于执行，须有活动或结果证据。每个派发任务收集结果，或保存明确取消及其确认状态。
按需或在结果、阻碍、审批、停滞、交接等事件发生时检查；长任务使用与风险和耗时相称的有界检查窗口，不默认每 60 秒巡查。quota 耗尽就停新派并保存成果；timeout、失联或 unknown 不证明未执行：先查原任务、活动、候选与 session，未知 writer 不 reset budget、不重复派工。取消未确认仍占预算，不能宣称退出或关闭；诊断无新证据时保存阻塞事实并报告，不无限轮询或偷换 provider。
人工接手先暂停 Bot 新指令与本任务自动发送，收集在途工作，确认 owner 和同一真实 session 后显式交接；Bot 只读观察。当前 owner 明确归还、在途状态与预算/去重核对后才恢复。idle、断连或关窗不是交接凭证，状态不明就保持暂停；不把现有连接或手写记录称作原子 fence。
冻结分支、HEAD/范围与已有候选证据后再审查。独立 reviewer 用未参与设计/实现的 session，只读候选，只写指定 review；advisor 不能改名审自己的设计，跨 provider 也不自动独立。提供原始材料和验收，不附作者自评或预期 verdict。审查结论须绑定同一候选，漂移使旧 PASS 失效。保留 finding、修复依据及复验结果；不能换 reviewer 刷 PASS，也不能把测试通过当独立审查或发布授权。
优先从真实输入到副作用追根因，审查同时挑战过度设计、fallback、双重 authority 和无消费者抽象。必要安全与验证保留，新增需求走范围变更；返工或争议不收敛时交用户裁定，保留 unresolved。
先保存证据，再清理
释放 owned 资源前，在 worktree 外保存可恢复代码/分支、有用 untracked、候选、验证、review/finding、对话证据，以及真实 sessionID、位置和恢复方式；脱敏并核验可读取/恢复。未保存、恢复失败、owner 不明或权限不足就保留资源并报告。正常退出 owned 进程，按实际资源确认处置；进程退出不等于 pane/Tab 已关闭，共享 Tab 保留并说明 owner/原因，不升级为 kill 主 Herdr/server 或关闭他人资源。worktree 清理单独判断，默认保留分支和历史。
最终报告实际成果、候选/PR、检查与审查结果、未验证能力、证据恢复位置和资源处置。格式检查只证明格式，源码接口存在只证明源码；隔离模拟、现场能力、验收和发布分别陈述，不用旧候选 PASS 覆盖修改后的 Skill。
© Ancienttwo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in docs/researches/development-scheduler/skill of Ancienttwo/repo-harness.
- SKILL.md
- references/hosts.md
- references/repo-harness.md
Open the folder on GitHubat commit 3ea2f7b
Compare with similar skills
Development Scheduler next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Development Scheduler this skillAncienttwo/repo-harness | 434 | — | ~703 | Automated safety check: Pass | MIT | |
| Agent Browserquran/quran.com-frontend-next | 1.9k | 42 repos | ~3.3k | Automated safety check: Pass | None | |
| Process Inboxtelegramdesktop/tdesktop | 33k | 2 repos | ~4.5k | Automated safety check: Pass | GPL-3.0 | |
| Perform Tasktelegramdesktop/tdesktop | 33k | 2 repos | ~3k | Automated safety check: Pass | GPL-3.0 | |
| Brave Searchbadlogic/pi-skills | 2.6k | 6 repos | ~592 | Automated safety check: Pass | MIT | |
| Continuetelegramdesktop/tdesktop | 33k | 2 repos | ~9.4k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Process Inbox
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
Perform Task
telegramdesktop/tdesktop
Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.
Brave Search
badlogic/pi-skills
Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.
Continue
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
Feishu Doc
openclaw/openclaw
Feishu document read/write workflows. An agent skill from openclaw/openclaw.
More from Ancienttwo/repo-harness
All 12 skills in this repoRepo Harness
Ancienttwo/repo-harness
Route explicit repo-harness commands and active harness work.
Repo Harness Chatgpt
Ancienttwo/repo-harness
Canonical rule owner for repo-harness ChatGPT integration -- Oracle-first browser/GPT Pro consult and continuation, advisory orchestration, MCP Connector setup, MCP bridge planning handoff, and…
Repo Harness Setup
Ancienttwo/repo-harness
Canonical rule owner for installing, migrating, upgrading, repairing, scaffolding, and capability-configuring the repo-harness workflow in a repository.
Repo Harness Ship
Ancienttwo/repo-harness
Close out verified harness work only when the user explicitly asks to commit, push, open a PR, merge, or clean merged worktrees.
Repo Harness
Ancienttwo/repo-harness
Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.
Repo Harness Check
Ancienttwo/repo-harness
Plan scoped harness work, review a plan, or assess recorded checks and risk.
Related
Categories
Questions about Development Scheduler
What does Development Scheduler do?
在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。. Development Scheduler is an agent skill from Ancienttwo/repo-harness.
When should I use Development Scheduler?
Development Scheduler fits situations like: productivity & Automation work in your project.
How do I install Development Scheduler in Claude Code?
Run `npx skills add Ancienttwo/repo-harness --skill development-scheduler -a claude-code`. Or copy the skill folder (docs/researches/development-scheduler/skill in Ancienttwo/repo-harness) into .claude/skills/development-scheduler in your project. Claude Code loads it when a task matches its description.
How do I install Development Scheduler in Codex?
Run `npx skills add Ancienttwo/repo-harness --skill development-scheduler -a codex`. Or copy the skill folder (docs/researches/development-scheduler/skill in Ancienttwo/repo-harness) into .agents/skills/development-scheduler in your project. Codex loads it when a task matches its description.
Can I use Development Scheduler in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ancienttwo/repo-harness --skill development-scheduler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/development-scheduler, .gemini/skills/development-scheduler, .github/skills/development-scheduler and .opencode/skills/development-scheduler in your project.
What does Development Scheduler need to run?
SKILL.md names no scripts, command-line tools or credentials: Development Scheduler is instructions for the agent only.
Does Development Scheduler access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Development Scheduler safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Development Scheduler use?
Development Scheduler is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Development Scheduler use?
About 703 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.
What are the alternatives to Development Scheduler?
Skills that share tags, products or a category with Development Scheduler: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Process Inbox (telegramdesktop/tdesktop, 33k stars), Perform Task (telegramdesktop/tdesktop, 33k stars) and Brave Search (badlogic/pi-skills, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Development Scheduler?
Ancienttwo (a GitHub user) maintains it in Ancienttwo/repo-harness, which has 434 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.
Source: Ancienttwo/repo-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.