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/lollipopkit/cc-plugins/devloopnpx skills add lollipopkit/cc-plugins --skill devloopgit clone --depth 1 https://github.com/lollipopkit/cc-pluginsWhat 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 | $0.00027 | $0.01484 |
| Opus 5 | $0.00014 | $0.00742 |
| Sonnet 5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
devloop 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你负责运行一个迭代式的工程循环，以解决用户提供的问题并将其推进到可以合并的 PR。你绝对不能直接合并到基准分支（例如 main），除非你明确询问用户并获得 APPROVED；否则，你必须始终打开 Pull Request 并等待审查。
强制工作流
你必须严格遵守以下顺序：
- 创建分支：如果当前分支是基准分支（例如
main），在进行任何更改之前，根据 issue 内容创建一个新的描述性分支。否则，跳过分支创建并继续在当前分支上工作。 - 实施修复：研究并实施修复。
- 本地验证：执行项目对应的测试集合以确保更改没有引入新的问题。如果测试失败，修复问题并重新运行测试，直到所有测试通过为止。
- Pull Request：创建一个清晰的提交消息并打开一个 PR 以供审查；PR 标题/描述模板优先参考最近一次 git commit msg（标题使用 commit msg，描述可复用 commit msg 或列出提交列表）。并且PR需要关联当前分支, 额外的, 如果用户提供了 issue，关联该 issue。
- 等待审查：轮询审查评论和 PR 合并状态（
MERGEABLE、UNKNOWN或CONFLICTING），轮询间隔为 60s，最多 30 次；达到上限后询问用户是否继续。 - 处理反馈：根据审查评论应用更改并再次提交/推送。
- 重复：迭代直到获得 APPROVED 且
mergeable状态为MERGEABLE。如果状态为UNKNOWN（正在计算），则继续轮询；如果状态为CONFLICTING（需要手动干预），则停止并通知用户。
核心职责：
- 确定问题来源（通过
ghGitHub，或本地文本/文件）。 - 如果该任务尚不存在 GitHub issue，在与用户确认后使用
gh issue create创建一个。 - 创建工作分支，实施修复，并保持更改范围受控（默认避免无关需求或大范围重构；但若为解决关键问题所必需，可进行重要重构并在说明中解释原因）。
- 当你认为一个连贯的单元完成时，提交更改。
专业性（至关重要 - 强制执行）
- Git 协议：对于已经推送到远程或已有开启 PR 的分支，严禁使用
git push --force、git push -f或git commit --amend。始终创建新的提交并使用标准的git push。 - 审查工具选择（动态判断）：每次执行本 skill 时都必须先动态检测本地是否可用
coderabbitCLI（如command -v coderabbit）。coderabbit仅作为推送前的本地前置检查：若可用，先在本地完成其报告问题修复并通过本地验证后再 push；若不可用或执行失败，跳过该前置检查并继续后续流程。 - 打开或更新 PR（默认 GitHub）并等待自动化/AI 审查反馈。
- 获取审查评论（默认 GitHub）并处理它们；重复提交/推送直到审查满意/APPROVED 且 PR 状态为
MERGEABLE。 - 当反馈建议进行不必要的更改时，询问用户是否继续。
- 一旦 PR APPROVE 且
mergeable状态为MERGEABLE，通知用户已准备好合并。将UNKNOWN视为“未就绪”：如果是UNKNOWN，继续轮询，因为 GitHub 仍在计算状态 - 如果用户没有指定什么issue/pr管理平台, 默认使用GitHub gh cli
- gh pr create 的时候, body 需要符合 markdown 格式, 包含详细的内容
- 如果和主线冲突无法合并, 先merge主线
操作规则：
- 除非明确要求，否则不要运行破坏性或不可逆的命令。
- 不要猜测 URL。仅使用用户提供的或
gh输出中的 URL。 - 流程优先级：本地前置检查优先使用
coderabbit（动态检测可用时），但远程审查/状态查询/PR 生命周期管理仍使用gh；其他 GitHub 操作默认使用gh，但也允许用户配置的自定义命令。 - 遇到无法执行、权限不足或关键信息缺失时，必须先询问用户。
猜测用户意图
- 修复 PR 评论：如果当前处于非主分支（如
main或master）且存在开启的 Pull Request，用户的意图通常是让你获取该 PR 的审查评论，修复这些问题并持续迭代，直到 PR 状态变为可合并。 - 修复特定 Issue：如果用户提供了 GitHub issue 链接，用户的意图是让你修复该 issue 描述的代码问题。如果 GitHub 上还没有对应的 issue，你应该在确认后创建一个，并随后提交 PR。
- 直接修复请求：如果用户直接描述了一个 Bug 或功能需求（例如“修复登录界面的对齐问题”），且没有提及具体 issue，你应该按照“强制工作流”创建新分支、实施修复并创建 PR。
- 错误日志驱动：如果用户粘贴了编译器错误或运行时堆栈信息并启用此技能，默认意图是让你定位该错误并完成修复到合并的完整循环。
- 多次迭代：
- 如果当前git存在未提交的更改,并且处于非主分支（如
main或master），你可能需要继续处理这些更改，直到它们被提交并推送，然后创建或更新 PR。 - 如果用户只是发送了"devloop"等, 你需要检查pr中剩余的没有被resolved的评论，并继续处理它们，直到所有评论都被解决并且pr可以合并。
- 如果当前git存在未提交的更改,并且处于非主分支（如
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.
- yesterday First seen · 58 lines · 27 tokens per session scan A dfe57e96f1ff
devloop is a skill published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,484 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 2026-08-31.
Other skills, from other repositories
modelchk
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…
re0-loop
Run repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.
autobahn
Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
re0-plan
Open a paperthin iteration's casebook before re0-loop's first turn — seeded with real content the moment the folder exists, never an empty directory. User-invoked, paperthin-only: assumes the full skill package installed. Run when opening a new build cycle in this repo.