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/martin1847/evolab/git-workflow-standardnpx skills add martin1847/evolab --skill git-workflow-standardgit clone --depth 1 https://github.com/martin1847/evolabWrote 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/martin1847/evolab/git-workflow-standard)<a href="https://agentmods.dev/skills/martin1847/evolab/git-workflow-standard"><img src="https://agentmods.dev/badge/skills/martin1847/evolab/git-workflow-standard.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.01640 |
| Opus 5 | $0.00050 | $0.00820 |
| Sonnet 5 | $0.00020 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
git-workflow-standard 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow（协作 SOP）
agent 与人共用的 Git 工作流规范。完整版 + rationale 见 references/git-workflow-standard.md。
双层落地:本 skill 是软层(write-time 预防)。不可逆动作(直推受保护分支、force push)的最终防线是硬层——GitHub Ruleset(归 你的 IaC 仓 / IaC CTO)。两者都在,不互替;硬层内部按三档 tier 渐进加码。
硬门禁契约（与服务端硬层对接缝，三档 tier）
canonical = 你的 IaC ruleset,本 skill 只镜像行为契约;具体仓的 enrollment 以 IaC 为准:
- Tier 1 baseline(所有仓,含未来仓):地板 = 禁 force-push + 禁删分支;不要求 PR、不强制线性历史 → 小仓 / 文档仓可直推、直接合。
- Tier 2 PR gate(显式白名单):require PR + 禁 force-push + 禁删分支;平台默认
required_approvals=0,允许作者 self-merge,不统一强制 CODEOWNERS / last-push approval / conversation resolution / linear history / status checks。跨人评审是建议,repo-local gate 明确升格时才是硬门。 - Tier 3 required CI(单独显式 enrollment):在 Tier 2 上叠加 required status checks;仅显式接入的仓生效,aggregate check MUST always-report(上游失败 / skip 也要产出终态),避免 required check 永久 pending。
下面「你 MUST 做的」是 Tier 2 / Tier 3 仓的 SOP;Tier 1 仓只需守 §5(提交信息)+ §6(受保护分支不 force-push),其余可简化(直推 / 直接合)。你的仓走哪档,在该仓 AGENTS.md 声明,agent 进仓先读。
你 MUST 做的
- 从最新 base 起 feature 分支:
git switch -c <type>/<slug>(feat/fix/chore/…),不在受保护分支上直接改。 - 受保护分支禁直推:
main/master/develop/dev/release/**/project/*一律走 PR,MUST NOTgit push直推、MUST NOTpush -f改写其历史。 - rebase 是条件动作、不是仪式:push/PR 前
git fetch,查 base 动没动(git log <branchpoint>..origin/<base>空 = 没动)。没动 → 什么都不做(空 rebase 是 no-op,不是漏步骤);动了且碰了你改的文件 → rebase 或把 base merge 进来解冲突再 PR;动了但文件不重叠 → 可不动。并发会话下fetch+检查必做,但"检查"≠"每次都 rebase"。评审/阅读用途的差分用 three-dot(origin/<base>...HEAD,merge-base 差分)——stale-base 两点差分会把他人 commit 的反向删除误读为回退;rebase 只服务 push/merge。 - 走 PR,只把已配硬门当硬门:PR 描述讲清 what/why;Tier 3 等 required checks 绿再合;review / CODEOWNERS / last-push / conversation resolution 仅在 repo-local gate 明确要求时阻断合并,否则跨人评审只是建议;合并方式按本仓声明的集成策略(见 §集成策略)。
- 提交信息:讲清意图,MUST NOT 加任何 AI / Claude 签名行 / co-author。
- force push 仅限自己的 feature 分支,优先
--force-with-lease;受保护分支永不 force。
集成策略（默认线性，2026-06-25 修订）
默认 squash;可选 rebase-merge(同为线性)。merge-commit 不是 sanctioned 选项。
- squash:线性、每 PR 一个原子全绿 commit、易 revert、bisect 友好 —— 默认。
- rebase-merge:偏好保留 PR 内分块 commit 且要线性的仓。
- 为何弃 merge-commit:全 agent、无人读 git 历史 → merge-commit 卖点失效(详见 references §4)。这是 SOP 默认,不是 Tier 2 服务端硬门;repo-local 若强制 linear 再按本地门执行。
- 对抗评审的知识(约束 / 被否方案)落 ADR + PR 记录 + commit trailer,不进 commit graph —— squash 丢 exhaust 不丢 knowledge。
- 合后判定:squash / rebase-merge 后原 head 不必是 base 的 ancestor,MUST NOT 用 ancestry 单独断言“未合入”或授权清理。历史合入查 forge 的精确 PR;当前内容查 tree / test;部署查不可变 release provenance(见 references §5.1)。
- 发布证据:release CI 对 exact pushed digest 完成 smoke 后、GitOps write-back 前,必须产出 immutable
release-evidence/v1(schema 见 references):只用service.versionrelease tag 贯穿部署,必含完整git_sha与image_digest;不另造release_id,也不把 SHA/digest 复制到每条 telemetry。
What ships with it
2 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.
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.
- 5d ago First seen · 51 lines · 100 tokens per session scan A 9c8a0510aa63
git-workflow-standard is a skill published in the GitHub repository martin1847/evolab (6 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,640 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 2026-08-31.
Other skills, from other repositories
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-llm-providers
Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…
continuum-temporal
Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…
continuum-agent
Build BaseAgent instances and run them with AgentRunner — covers fields, lifecycle hooks, structured outputs, ReAct mode, instruction modifiers, and the full execution flow. Invoke when the user asks "create an agent", "configure maxturns", "add lifecycle hooks", "structured output with Pydantic", or anything around…