spec

A command that turns a feature idea or ticket into a written software specification with clear acceptance criteria.

In plain words
What is it for?
Use it with plain text or a reference to a JIRA, GitHub, Linear, or Azure work item to create a feature specification.
Why use it?
It gives the team a shared description of what to build and what counts as complete before planning or coding begins.

Command for Claude Code

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 commands/loiane/specs-driven-development-spring-angular/spec
Clone the repo
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00017 $0.00574
Opus 5 $0.00009 $0.00287
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash 972f62c0a1f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/commands/spec.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec

Phase: 1 — specify Owning agent: .claude/agents/spec-author.md Skills used: ears-spec-authoring, issue-tracker-ingestion, requirements-traceability

Purpose

Turn raw intent (a sentence, a paragraph, or a ticket URL) into a complete EARS-style specification at .specs/<feature-id>/01-spec.md.

Inputs

Either:

  • Free text describing the feature, OR
  • A ticket reference (JIRA-123, GitHub issue URL, Linear ID, Azure work item URL).

If a ticket is supplied, fetch it via the configured MCP server (see .claude/skills/issue-tracker-ingestion/SKILL.md) and treat its body as the source.

Reads

  • The supplied text or ticket.
  • .specs/_onboarding.md (for stack context).
  • .claude/templates/spec.template.md.
  • .claude/checklists/spec-review.md (so the spec is born review-ready).

Writes

  • .specs/<feature-id>/01-spec.md (feature-id = kebab-case slug derived from the title, prefixed with date YYYY-MM-DD-).

Process

  1. Derive <feature-id>. Refuse if a folder with that id already exists unless the user passes --continue.
  2. Extract: business goal, primary actor, in-scope, explicitly-out-of-scope.
  3. Write acceptance criteria as AC-001, AC-002, ... using strict EARS forms (Ubiquitous, Event-driven, State-driven, Unwanted-behavior, Optional). Every AC must be testable.
  4. List non-functional requirements (latency, throughput, security, observability) with concrete numbers. If unknown, file an Open Question instead of guessing.
  5. Capture Open Questions as Q-001, Q-002. Never invent answers. Stop and surface the questions to the user.
  6. Render the file using .claude/templates/spec.template.md.

Refuse if

  • The input has fewer than 3 distinct nouns/verbs (likely too vague — ask the user to expand).
  • Any acceptance criterion would require unstated assumptions.

Done when

  • 01-spec.md exists with at least one AC and zero invented answers.
  • All ambiguities are listed under ## Open Questions with Q-NNN IDs.
  • The user has been told the next command is /spec-review (after they answer any Q-NNN).

Read the full file on GitHub · 47 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 · 47 lines · 17 tokens per session scan A 972f62c0a1f6

Subscribe to this mod's changes

spec is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (57 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 574 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 2026-08-30.