Agent skill

Openspec Workflow Router

by HsienW in HsienW/chat-gun

MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts.

Custom licenceAuto-check passedAI & LLM Engineering

Install Openspec Workflow Router

skills CLI
$ npx skills add HsienW/chat-gun --skill openspec-workflow-router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HsienW/chat-gun openspec-workflow-router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HsienW/chat-gun.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/openspec-workflow-router .claude/skills/openspec-workflow-router && rm -rf skills-src

Use ~/.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/

Facts

Skill name
openspec-workflow-router
GitHub stars
143
Token cost
~907 tokens
SKILL.md length
426 words
Files
9 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts.

  • Works in 8 steps: Decide whether the request belongs to… → If a change name is known, read only… → If CurrentState exists, use currentPhase… → …
  • The user asks Codex to plan
  • SKILL.md covers Task-Start Awareness, Context Policy, Runtime Artifact Boundary and Route Table, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Openspec Workflow Router is an agent skill from HsienW/chat-gun. MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts. Use when the user asks Codex to plan, review, implement, fix, readiness-check, archive, or coordinate an OpenSpec change, especially with CCR/Qwen/Codex handoffs.

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `agents/openai.yaml`, `references/01-plan-change.md` and `references/02-review-plan.md`).

It sits in AI & LLM Engineering. It works with Qwen. The repository describes itself as: 🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable…

When your agent uses it

  • The user asks Codex to plan
  • Readiness-check
  • Coordinate an OpenSpec change
  • Especially with CCR/Qwen/Codex handoffs

Example prompts

  • “/openspec-workflow-router”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Decide whether the request belongs to the OpenSpec change lifecycle.
  2. If a change name is known, read only .agent-runtime//current-state.json even though .agent-runtime/ is ignored.
  3. If CurrentState exists, use currentPhase as the source of truth and verify currentOwner; reject a conflicting requested stage.
  4. Select exactly one stage and read only that reference.
  5. Read only artifacts named by latestArtifactRefs or the current Handoff requiredInputRefs.
  6. If CurrentState is missing, only CCR may initialize it during plan-change; every other role or stage must stop.
  7. If it is not a lifecycle task, keep the context policy below in force and continue with the normal project rules.
  8. If another host owns the stage, produce the handoff prompt or perform only the requested role.

What it can do on your machine

Read from SKILL.md and the folder at commit 4569cb0. 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

Openspec Workflow Router loads about 907 tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 426 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~907
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 426 words (~907 tokens).

“Use this skill as a routing layer. Do not load every reference. Pick one stage, then read only its reference file.”

— opening of SKILL.md by HsienW, Custom licence
name
openspec-workflow-router

Read the full SKILL.md on GitHub

Files

SKILL.md and 8 other files (references) in .codex/skills/openspec-workflow-router of HsienW/chat-gun.

  • SKILL.md
  • agents/openai.yaml
  • references/01-plan-change.md
  • references/02-review-plan.md
  • references/03-apply-change.md
  • references/04-review-result.md
  • references/05-fix-from-review.md
  • references/06-readiness-check.md
  • references/07-archive-change.md

Open the folder on GitHubat commit 4569cb0

Compare with similar skills

Openspec Workflow Router 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.

Openspec Workflow Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openspec Workflow Router this skillHsienW/chat-gun143—~907Automated safety check: PassCustom licence
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0
Train SftOpenPipe/ART11k—~2.9kAutomated safety check: PassApache-2.0
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide1.7k—~1.7kAutomated safety check: PassMIT
Dingo VerifyMigoXLab/dingo757—~833Automated safety check: PassApache-2.0
Veomni New ModelByteDance-Seed/VeOmni2.2k—~2kAutomated safety check: PassApache-2.0

Similar skills

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Train Sft

    OpenPipe/ART

    SFT training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.9k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Qwen Mtp Gguf

    R6410418/Jackrong-llm-finetuning-guide

    Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

    1.7k GitHub stars~1.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Dingo Verify

    MigoXLab/dingo

    A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

    757 GitHub stars~833 tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed
  • Veomni New Model

    ByteDance-Seed/VeOmni

    A skill your agent uses when adding support for a new model to VeOmni.

    2.2k GitHub stars~2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • slime RL Post-Training

    Orchestra-Research/AI-Research-SKILLs

    Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

    13k GitHub starsUsed in 5 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed

More from HsienW/chat-gun

All 8 skills in this repo
  • Chat Gun 的前端、OpenSpec、Streaming Event、Tool Renderer、型別邊界、多模態流式鏈路與 React/Vite 編程約束。Use when working on frontend code, tool rendering, streaming contracts, multimodal requests/responses, Weather…

    143 GitHub stars~467 tokensUpdated 4 days ago
    Auto-check passed
  • Node

    HsienW/chat-gun

    Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error handling, streams, modules, testing, performance, caching, logging…

    143 GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed
  • MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route Claude Code/CCR coordination tasks without loading unnecessary context.

    143 GitHub stars~939 tokensUpdated 4 days ago
    Auto-check passed
  • MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route Qwen Code review tasks without loading unnecessary context.

    143 GitHub stars~923 tokensUpdated 4 days ago
    Auto-check passed
  • 對 OpenSpec、Git Diff、frontend、bff、backend、LangGraph、Tool、MCP 與安全邊界進行獨立唯讀審查,輸出 Blocker、Major、Minor 與標準 Verdict。

    143 GitHub stars~775 tokensUpdated 4 days ago
    Auto-check passed
  • Apply when creating, modifying, refactoring, debugging, testing, or reviewing TypeScript, LangGraph JS, LangChain, provider adapter, tool, MCP, prompt, state, checkpoint, runtime event, or backend…

    143 GitHub stars~2.1k tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Openspec Workflow Router

What does Openspec Workflow Router do?

MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts. Openspec Workflow Router is an agent skill from HsienW/chat-gun. MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts.

When should I use Openspec Workflow Router?

Openspec Workflow Router fits situations like: the user asks Codex to plan; readiness-check; coordinate an OpenSpec change; especially with CCR/Qwen/Codex handoffs.

How do I install Openspec Workflow Router in Claude Code?

Run `npx skills add HsienW/chat-gun --skill openspec-workflow-router -a claude-code`. Or copy the skill folder (.codex/skills/openspec-workflow-router in HsienW/chat-gun) into .claude/skills/openspec-workflow-router in your project. Claude Code loads it when a task matches its description.

How do I install Openspec Workflow Router in Codex?

Run `npx skills add HsienW/chat-gun --skill openspec-workflow-router -a codex`. Or copy the skill folder (.codex/skills/openspec-workflow-router in HsienW/chat-gun) into .agents/skills/openspec-workflow-router in your project. Codex loads it when a task matches its description.

Can I use Openspec Workflow Router 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 HsienW/chat-gun --skill openspec-workflow-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openspec-workflow-router, .gemini/skills/openspec-workflow-router, .github/skills/openspec-workflow-router and .opencode/skills/openspec-workflow-router in your project.

What does Openspec Workflow Router need to run?

SKILL.md names no scripts, command-line tools or credentials: Openspec Workflow Router is instructions for the agent only.

Does Openspec Workflow Router 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 Openspec Workflow Router 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 Openspec Workflow Router use?

Openspec Workflow Router has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Openspec Workflow Router use?

About 907 tokens (SKILL.md is roughly 3.6k 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 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Openspec Workflow Router?

Skills that share tags, products or a category with Openspec Workflow Router: Train Rl (OpenPipe/ART, 11k stars), Train Sft (OpenPipe/ART, 11k stars), Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Dingo Verify (MigoXLab/dingo, 757 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openspec Workflow Router?

HsienW (a GitHub user) maintains it in HsienW/chat-gun, which has 143 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 4, 2026.

Source: HsienW/chat-gun on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.