speckit-workflow

speckit-workflow is a skill for Claude Code from arrrrny/zuraffa. It costs 30 tokens per session (3,657 once invoked), scanned A, original, MIT.

An automated workflow for Specification-Driven Development, where a feature is described before it is planned, broken into tasks, and built. It runs this process in the Zed code editor without stopping for approval.

In plain words
What is it for?
Use it to take a feature request through specification, implementation planning, task creation, and coding in a Zed project.
Why use it?
It removes the need to coordinate each planning and implementation step manually. When details are missing, it searches the project and chooses a reasonable default.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ahmettok/Developer/zuraffa.

Good fit Use it to take a feature request through specification, implementation planning, task creation, and coding in a Zed project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for speckit-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-workflow.svg)](https://agentmods.dev/skills/arrrrny/zuraffa/speckit-workflow)
Your own site
<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-workflow"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,657 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.03657
Opus 5 $0.00015 $0.01828
Sonnet 5 $0.00006 $0.00731
Haiku 4.5 $0.00003 $0.00366

Measured yesterday against content hash f986436e76e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speckit-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 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.

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.

.agents/skills/speckit-workflow/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speckit Workflow (Zed) — Autonomous Mode

Run the full Specification-Driven Development lifecycle within Zed without any user interaction. This skill orchestrates the sequential execution of:

  1. Pre-Flight — System context & project health
  2. /speckit-specify — Create/update the feature specification
  3. /speckit-plan — Generate the implementation plan
  4. /speckit-tasks — Generate actionable tasks
  5. /speckit-implement — Execute the implementation

No review gates. No questions. No stops. If information is missing, search the project codebase for the answer. If truly blocked, make a reasonable default decision and continue.

User Input

$ARGUMENTS

Parse the user input for the following:

Required:

  • Feature description — A natural language description of what to build.

Optional (extracted from input if present):

  • scope — One of full, cli-only, generator-only, plugins-only, docs-only. Defaults to full.
  • branch — An explicit branch name to use (e.g., --branch my-feature). If not provided, the speckit-git-feature hook auto-generates one.

If no feature description is provided, stop immediately — do not ask the user to clarify. The workflow cannot proceed without a description.

When you encounter any ambiguity or missing information during any step:

  1. Search the project: Use grep, find_path, or claude_context_search_code to find existing patterns in the codebase.
  2. Read the docs: Check docs/ for architecture documentation — these contain high-level system understanding.
  3. Check existing specs: Look at specs/ directory for similar features to understand conventions.
  4. Check existing implementations: Look at the actual code in lib/src/ for established patterns.
  5. Scan AGENTS.md: Contains project-specific rules and conventions for v5.
  6. Use prior features: Check specs/ for closely related features — their specs, plans, and tasks.md files document existing patterns.
  7. Check .zfa/ memory: The .zfa/ directory contains project memory — plans, runs, decisions, blueprints, manifests, and context.

Read the full file on GitHub · 332 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 Changed · -13 lines f986436e76e3
  2. 8d ago First seen · 345 lines · 30 tokens per session scan A 29e83ccfc1d1

Subscribe to this mod's changes

speckit-workflow is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,657 once invoked, about $0.0002 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.