set-core: Skill for Claude Code

.claude/skills/set/write-spec/SKILL.md

write-spec is a skill for Claude Code from tatargabor/set-core. It costs 53 tokens per session (1,964 once invoked), scanned A, original, MIT.

An interactive specification-writing assistant that turns a project idea into a structured list of requirements and expected behaviours. It adapts the sections to the detected project type and can split large projects into smaller specification files.

In plain words
What is it for?
Use it to discover project context, ask planning questions, and produce implementation-ready specifications for projects with one or more features.
Why use it?
It helps prevent vague or incomplete requirements before implementation starts. Each requirement gets a clear identifier and a WHEN/THEN example describing the expected result.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

This is tatargabor/set-core's own configuration. It tells Claude Code how to work on set-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything set-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tatargabor/set-core/main/.claude/skills/set/write-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-core

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 write-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatargabor/set-core/write-spec.svg)](https://agentmods.dev/skills/tatargabor/set-core/write-spec)
Your own site
<a href="https://agentmods.dev/skills/tatargabor/set-core/write-spec"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/write-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,964 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 $0.00053 $0.01964
Opus 5 $0.00026 $0.00982
Sonnet 5 $0.00011 $0.00393
Haiku 4.5 $0.00005 $0.00196

Measured yesterday against content hash 2ab8b6d92aac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

write-spec 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/set/write-spec/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Spec — Profile-Driven Specification Generator

Guide the user through writing a detailed project specification. The spec is the most important input to the orchestration pipeline — spec quality directly determines output quality.

Key principles:

  • Requirements describe WHAT, not HOW (no code blocks, no file paths)
  • Every requirement gets a REQ-ID and at least one WHEN/THEN scenario
  • Modular output for projects with 3+ features (main + per-feature files)
  • Profile-driven: web projects get data model, seed, auth sections; others get core only

Workflow

Phase 0: Project Context Detection + Profile Loading

Before asking questions, detect the project type and load spec sections:

# Detect project type and tech stack
ls package.json pyproject.toml Cargo.toml go.mod Makefile docker-compose.yml 2>/dev/null
cat package.json 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print('Name:', d.get('name','')); deps=list(d.get('dependencies',{}).keys()); print('Deps:', ', '.join(deps[:15]))" 2>/dev/null
ls prisma/schema.prisma 2>/dev/null && echo "Prisma detected"
ls docs/*.make docs/design.make docs/design-system.md 2>/dev/null && echo "Design files detected"

Load profile sections:

python3 -c "
from set_orch.profile_loader import resolve_profile
import json
p = resolve_profile('.')
sections = [{'id':s.id,'title':s.title,'description':s.description,'required':s.required,'phase':s.phase,'output_path':s.output_path,'prompt_hint':s.prompt_hint} for s in p.spec_sections()]
print(json.dumps(sections, indent=2))
" 2>/dev/null

If profile loading fails (set-core not installed as package), use these fallback core sections:

  • overview (phase 1) — Project name, purpose, tech stack
  • requirements (phase 5) — Main features with REQ-IDs and scenarios
  • orchestrator_directives (phase 10) — Parallel hints, review gates
  • verification_checklist (phase 11) — Auto-generated from requirements

If the tech stack is unfamiliar, use the Agent tool (Explore subagent) to investigate before proceeding.

Read the full file on GitHub · 219 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 · 219 lines · 53 tokens per session scan A 2ab8b6d92aac

Subscribe to this mod's changes

write-spec is a skill published in the GitHub repository tatargabor/set-core (35 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,964 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 2026-09-06.

Related

Other skills, from other repositories

atmos-migration

This skill helps you migrate a repository to Atmos. It covers native Terraform, Terraform Workspaces, Terramate, Terragrunt, Makefiles, Justfiles, and Taskfiles. It gives minimum-disruption paths, file-layout options, workspace mapping, task-to-command mapping, generatehcl/script decomposition, and the remote-state…

cloudposse/atmos · 96 tokens

atmos-modernization

Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.

cloudposse/atmos · 36 tokens

atmos-init

Bootstrapping new Atmos projects with atmos init: built-in template catalog, differences from atmos scaffold generate, project record, and update-safe 3-way merge.

cloudposse/atmos · 35 tokens

atmos-workflows

Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries, dependencies, and cross-component orchestration.

cloudposse/atmos · 49 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

atmos-imports

Atmos imports: local and remote stack imports, go-getter schemes, templated imports, import context, remote imports vs component source/vendoring, and private GitHub imports through github/sts.

cloudposse/atmos · 44 tokens