spec

spec is a command for Claude Code from artemnovichkov/skills. It costs 25 tokens per session (514 once invoked), scanned A, original, MIT.

A specification command that turns an accepted intent into a document of testable requirements and a design. It reads the repository's conventions, architecture, policies, and affected code before writing the specification.

In plain words
What is it for?
Use it to define what a change must do, how it should fit the existing system, and what should remain untouched.
Why use it?
It reduces guesswork by connecting the requested outcome to real code, constraints, interfaces, and rejected alternatives before implementation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc plugin — 1 skill, 8 commands, 1 agent, 1 hook shipped together

Good fit Use it to define what a change must do, how it should fit the existing system, and what should remain untouched.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add artemnovichkov/skills
Claude Code
/plugin install sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 agent, 1 hook.

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 spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/artemnovichkov/skills/spec/github.svg)](https://agentmods.dev/commands/artemnovichkov/skills/spec)
Your own site
<a href="https://agentmods.dev/commands/artemnovichkov/skills/spec"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec

Your own site · 80×15
<a href="https://agentmods.dev/commands/artemnovichkov/skills/spec"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00025 $0.00514
Opus 5 $0.00013 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash b5f67d257913, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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.

skills/sdlc/commands/spec.md · 45 lines

What it actually says

Stage 2 — Requirements and design collapse into one session

Requirements analysis and design happen in the same session. The point is not speed for its own sake: policy gets applied while the spec is written instead of being discovered in review later.

$ARGUMENTS is the slug. If empty, list sdlc/intent/ and ask which intent to work from.

Workflow

1. Load the constraints

  • Read sdlc/intent/<slug>.md. If its Status: is not accepted, say so and ask whether to proceed anyway.
  • Read CLAUDE.md for repo conventions and architecture.
  • Load whatever policy the repo carries: skills in .claude/skills/, CONVENTIONS.md, ARCHITECTURE.md, security or style docs. These are the constraints the spec must satisfy.
  • Read the code the intent touches. A spec written without reading the affected files is guesswork.

2. Draft the spec

Use ${CLAUDE_PLUGIN_ROOT}/templates/spec.md and write sdlc/spec/<slug>.md:

  • Requirements as testable statements, each traceable to something in the intent.
  • Design: the approach, the data/state changes, the interfaces that move, what stays untouched.
  • Alternatives considered, with the reason each was dropped — one line each.
  • Concerns, explicitly flagged: anything where the design collides with a repo convention, a security or privacy surface, a migration, a performance cliff, or an open question the intent left unresolved. Flag it; do not resolve it silently.
  • Answer every open question from the intent, or restate it as a concern.
  • Status: draft.

3. Resolve concerns with the user

Walk the concerns one at a time. Each ends as: resolved (with the decision recorded in the spec), accepted risk (recorded as such), or deferred to a follow-up intent.

4. Accept and commit

Flip to Status: accepted once the user agrees, then print:

git add sdlc/spec/<slug>.md && git commit -m "spec: <title>"

Next step: /sdlc:plan <slug>.

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 · 45 lines · 25 tokens per session scan A b5f67d257913

Subscribe to this mod's changes

spec is a command published in the GitHub repository artemnovichkov/skills (36 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 514 once invoked, about $0.0001 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 2026-09-07.