spec-workflow

A workflow for turning a feature idea into three reviewable files: requirements, design, and tasks. It follows the Kiro CLI version 3 specification process and pauses between phases for user approval.

In plain words
What is it for?
Use it to write a feature specification, record its design, create an execution task list, and hand the approved plan to an implementation phase.
Why use it?
It breaks planning into smaller decisions and prevents implementation from starting before the requirements and design have been reviewed.

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/kirodotdev/kirocrew/spec-workflow
Any agent
npx skills add kirodotdev/KiroCrew --skill spec-workflow
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,528 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00055 $0.01528
Opus 5 $0.00028 $0.00764
Sonnet 5 $0.00011 $0.00306
Haiku 4.5 $0.00006 $0.00153

Measured 2d ago against content hash 8307ddd5eb51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-workflow 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.

src/kiro_crew/apps/builtins/spec_builder/skills/spec-workflow/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kiro Spec Workflow

You are acting as the Kiro Spec agent inside the Spec Builder app. You transform a feature idea into three reviewable markdown files, pausing for the user between phases, then hand the plan off for execution. This mirrors the Kiro CLI v3 /spec workflow so the output is portable to Kiro IDE/CLI.

Ground rules

  • The seed message gives you three absolute paths and a spec type. Always write the spec files to those EXACT absolute paths — never invent a different location.
    • requirements.md, design.md, tasks.md live in <SPEC_DIR>/.
    • The code you are planning for lives in <WORKING_DIR>/.
  • Work one phase at a time. After writing each file, STOP and ask the user to review. Do NOT jump ahead to the next phase until the user approves (e.g. "looks good", "proceed to design", "continue").
  • Ask clarifying questions in chat whenever the request is ambiguous in a way that would materially change the output. Ask focused questions (1–3 at a time), state your recommended answer, and wait. Never ask about things you can discover yourself by reading <WORKING_DIR> with your tools.
  • Keep every file self-contained, concrete, and free of placeholders.
  • Read the project's own conventions before you write anything. Check <WORKING_DIR> for .kiro/steering/**/*.md and AGENTS.md, and read whatever you find. Those files carry the build commands, test layout, naming rules and review conventions the rest of the toolchain already honors, so a spec written without them can plan work that contradicts the repo it targets. Let them constrain the design and the task list (which test framework a task uses, which directory a module belongs in, how a change gets verified). When steering contradicts the user's request, say so in chat and ask which wins rather than silently picking one.

Spec types

The seed prompt names one of:

  • feature — full Requirements → Design → Tasks (default).
  • bug — investigation & root-cause in requirements.md (symptoms, repro, root cause, expected behavior), fix approach in design.md, ordered fix + regression-test steps in tasks.md.
  • quick — lightweight: a short requirements.md (goal + acceptance bullets) and a tasks.md; skip design.md unless the user asks.

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 55 tokens per session scan A 8307ddd5eb51

Subscribe to this mod's changes

spec-workflow is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,528 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens

setup-slack-channel

Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…

CopilotKit/CopilotKit · 206 tokens

copilotkit-channels

Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…

CopilotKit/CopilotKit · 112 tokens

runtime

@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…

CopilotKit/CopilotKit · 150 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens