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/magebyte-zero/spec-superflow/workflow-startnpx skills add MageByte-Zero/spec-superflow --skill workflow-startgit clone --depth 1 https://github.com/MageByte-Zero/spec-superflowWhat 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 | $0.00125 | $0.04128 |
| Opus 5 | $0.00063 | $0.02064 |
| Sonnet 5 | $0.00025 | $0.00826 |
| Haiku 4.5 | $0.00013 | $0.00413 |
Grade A, and why
workflow-start 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 2d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Start
Primary entry point for spec-superflow. Jobs: inspect change context, check for updates, confirm DP-0, determine state, route to correct skill, block invalid transitions.
Use This Skill When
Only invoke when spec-superflow context is present: .spec-superflow.yaml exists, artifacts like proposal.md/specs//design.md/tasks.md/execution-contract.md are present, or user explicitly invokes spec-superflow by name. When in doubt, check for .spec-superflow.yaml first.
Do NOT invoke for: general coding tasks outside spec-superflow changes, casual questions, unrelated work.
States
exploring → specifying → bridging → approved-for-build → executing → closing, with debugging side-path from executing, and abandoned as terminal. After closing, Full/legacy Hotfix changes complete the physical archive with ssf finish (owned by release-archivist); lightweight paths end at closing itself. If a transition is ambiguous, run ssf runtime asset read docs/state-machine.md.
Terminal-State Short Circuit
Before update checks or recovery overlays, inspect the persisted state. If it is
closing, stop immediately: closing is a successful terminal state and the
next skill is none. Report the terminal state and its persisted evidence.
Do not run handoff list, checkpoint list, the execution-control recovery
scan, or release-archivist; do not resume, hand off, or route any more work.
Note: closing is the logical terminal of the state machine; the physical archive (merge + worktree cleanup) for Full/legacy Hotfix is performed by ssf finish in release-archivist. Lightweight paths have no physical archive step.
Initialization
- Update check: Run
ssf runtime check-update. Exit 0 → continue. Exit 1 → non-blocking upgrade reminder. Exit 2 → skip. - Inspect change folder: Check for
proposal.md,specs/,design.md,tasks.md,execution-contract.md. Answer: Is the change fuzzy? Artifacts missing/unstable? Contract exist? User approved contract? Execution in progress or blocked? In verification/wrap-up?
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.
- 2d ago First seen · 263 lines · 125 tokens per session scan A 029137c0b76b
workflow-start is a skill published in the GitHub repository MageByte-Zero/spec-superflow (776 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 4,128 once invoked, about $0.0006 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
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.
workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。.
plan
Turns an approved design or decided brief into ordered tasks for separate agent runs. Use for implementation tasks, tracker tickets, or useful milestones. Do not use for one coding task or its short execution outline.