workflow-setup

A setup helper for Workflow, a project-management service, that connects your account, API token, and selected project.

In plain words
What is it for?
It registers or connects an account, saves token settings, checks the current user and project, and adds or switches project profiles.
Why use it?
It helps diagnose missing credentials, failed access, incorrect projects, and permission problems before you perform work in Workflow.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/go1c/workflow-plugin/workflow-setup
Any agent
npx skills add Go1c/workflow-plugin --skill workflow-setup
Clone the repo
git clone --depth 1 https://github.com/Go1c/workflow-plugin

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.02912
Opus 5 $0.00035 $0.01456
Sonnet 5 $0.00014 $0.00582
Haiku 4.5 $0.00007 $0.00291

Measured yesterday against content hash 032c777c53b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-setup scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl 携带 token 一律走环境变量,不把明文拼进命令行:
skills/workflow-setup/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

workflow-setup — 接入 Workflow 并验证连接

完成判据(先看这个)

GET $WORKFLOW_API_BASE/me 返回 200,且 GET $WORKFLOW_API_BASE/projects/current 返回 200;从前者读用户,从后者读 projectmembership,再向用户报告:「以 <用户名> 连接到项目 <项目>,角色 <角色>」。没走到这一步,接入就不算完成——中间任何分支做完都要回到这条验证。

这只证明身份、项目和角色连接正确,不证明 PAT scope 可写;membership.permissions 是角色侧权限。不要为了测试 scope 创建或修改业务对象,真正写操作若返回 403 再按权限分诊。

Step 0 — 静默探测(每次都先做,不问用户)

workflow-ops/references/connection.md 的**凭证解析顺序(三级)**取 base_url 与 token——三级规则、API 根地址规范化和可抄的 shell 片段都在那份共享文件里,本技能不另写一份。

取到凭证 → 依次探测 GET $WORKFLOW_API_BASE/meGET $WORKFLOW_API_BASE/projects/current。两者通过且项目与 profile 一致 → 直接按完成判据报告,结束本技能。探测失败或全局 config 不存在 → 按下面分支走。

curl 携带 token 一律走环境变量,不把明文拼进命令行:

curl -sS -H "Authorization: Bearer $WORKFLOW_TOKEN" "$WORKFLOW_API_BASE/me"
curl -sS -H "Authorization: Bearer $WORKFLOW_TOKEN" "$WORKFLOW_API_BASE/projects/current"

项目绑定与多项目(.workflow 标记)

一台机器接多个项目时,插件全局只装一份、config.toml 每项目一节 profile,项目目录用 .workflow 标记文件声明「这个目录绑哪个 profile」:

  • 位置:项目仓库根(或当前工作目录)。查找规则:从当前目录向上逐级找,取最近的一个,到含 .git 的目录或文件系统根为止。
  • 内容:一行 TOML——profile = "<profile 名>"(双引号);允许整行 # 注释(不支持行内注释,会导致解析落空)。顶层仅此一键;另可有一个可选的 [qa] 表供 workflow-qa 读取受测线上地址与凭据的环境变量名(见下)。整个文件不含 token 也不含任何凭据,可提交进版本库与全队共享(每人的 token 仍在各自全局 config 里)。
  • 写入时机:setup 完成项目绑定时问用户「要不要把绑定写进当前项目(.workflow 文件)」,默认写。
  • 解析落空 = 停止,不回落.workflow 存在但读不出 profile 名(写了行内注释、用了单引号、键名拼错)时,必须停下让用户修,绝不悄悄改用全局 current_profile——那正好会把数据写进另一个项目,是这套绑定机制要防的唯一一件事。

可选的 [qa] 表(只有用 workflow-qa 做线上验收时才需要,setup 不主动追问):

profile = "<profile 名>"

[qa]
base_url = "https://<受测线上站点>"
entry_path = "/<登录或入口路径>"
username_env = "<用户名环境变量名>"
password_env = "<密码环境变量名>"
surfaces = ["web"]

只写环境变量名,绝不写用户名或密码本身——这个文件是要提交进版本库的。字段口径以 workflow-qa 的 references/qa-environment.md 为准。

.workflow 是独立文件,绝不合并进 config.toml——config.toml 的格式合同一个键都不能加(见分支 C 的写盘规则),[qa] 只属于 .workflow

权限模式策略

读取 workflow-ops/references/permission-modes.md。 权限不写入凭证文件:用户级策略在 ~/.config/workflow/policy.toml,项目级降权覆盖在 .workflow-policy。缺失时默认 auto;未知模式或策略解析失败时停止所有线上写入。向用户报告 当前 profile、项目覆盖和最终生效模式;full 只能由用户级 profile 显式开启,项目文件不得升权。 策略模式不等于 PAT scope,不以探测性 POST 验证权限。项目级 .workflow-policy 只能降权;本地 .workflow-drafts/ 是待上传 outbox,setup 和 token 配置流程不得覆盖、清理或上传其中内容。

Read the full file on GitHub · 136 lines

Changes

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.

  1. yesterday First seen · 136 lines · 70 tokens per session scan A 032c777c53b2

Subscribe to this mod's changes

workflow-setup is a skill published in the GitHub repository Go1c/workflow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 2,912 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.