spec-first

A process for writing a clear specification before building a feature or product slice.

In plain words
What is it for?
It helps document the overview, user stories, acceptance criteria, files to read, constraints, non-goals, and unresolved questions in a project spec.
Why use it?
It turns an idea into agreed, checkable requirements so developers and testers know what the software must do and what is out of scope.

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/missingpackage/nightshift/spec-first
Any agent
npx skills add MissingPackage/nightshift --skill spec-first
Clone the repo
git clone --depth 1 https://github.com/MissingPackage/nightshift

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 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 $0.00057 $0.00481
Opus 5 $0.00028 $0.00241
Sonnet 5 $0.00011 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured yesterday against content hash 94479b9f5a66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-first 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/spec-first/SKILL.md · 43 lines

What it actually says

Spec First

Overview

The spec shape below is salvaged from this workspace's own best specs (the Feb 2026 MVP voice pipeline, a research-site brief) — the SpecKit engine is retired, the shape earned its keep. A spec is the PI's judgment made editable; the draft saves typing, the edit IS the judgment.

The shape (write to specs/<slug>.md, or .harness/goals/<slug>/SPEC.md when goal-bound)

# <Feature name>
## Overview            — one paragraph: what and why now
## User stories        — each: As/I want/so that + Acceptance criteria that are
                         OBSERVABLE BEHAVIORS (a tester could check each box)
## Read first          — table: What | Where | Why (files the implementer must
                         understand before writing code)
## Non-goals           — what this slice deliberately does NOT do
## Hard constraints    — tech, UX, budget, deadline ("demo tra X giorni" goes HERE,
                         not in a firefight message later)
## Open questions      — every inference marked [ASSUMED: …]; unresolved = not approved

Rules

  • Acceptance criteria must be checkable without interpretation ("routing happens silently — no voice prompt about choosing a mode" is checkable; "good UX" is not).
  • Draft fast, mark every guess [ASSUMED], and hand back for editing. Never proceed to implementation with unresolved [ASSUMED] markers — the user's edit of those markers is the load-bearing judgment, not a formality.
  • The Read-first table is for the NEXT agent, not the user: real paths, one-line why each.
  • Slice scope: if the stories exceed what SDD can verify in a few tasks, split the spec.

When NOT to use

Bug fixes (skill: root-cause), one-file changes, research experiments (predictions + directive files own that lane).

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 · 43 lines · 57 tokens per session scan A 94479b9f5a66

Subscribe to this mod's changes

spec-first is a skill published in the GitHub repository MissingPackage/nightshift (2 stars, last pushed 16d ago), licensed MIT. It adds 57 tokens to every session and 481 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 2026-08-31.

Related

Other skills, from other repositories

baton-setup

One-time setup and health check for fable-baton. Use when the user asks to set up, configure, verify, or troubleshoot fable-baton - sets the default model to "best" (Fable 5 with Opus fallback) in /.claude/settings.json and verifies the plugin is fully installed.

realgarit/fable-baton · 69 tokens

licensing-tiers-data-governance

Implement subscription tiers with field-level access control, feature gating, rate limiting, and compliance tracking. Design data governance systems that enforce different access levels, retention policies, and regulatory requirements based on user subscription tier (Free, Pro, Enterprise).

sunnypatneedi/claude-starter-kit · 56 tokens

data-infrastructure-at-scale

Build data infrastructure that scales from prototype to production. Use when architecting data pipelines, choosing data stores, planning for high throughput, or migrating to distributed systems. Covers caching, replication, sharding, message queues, and data lake architecture.

sunnypatneedi/claude-starter-kit · 56 tokens

data-provenance

Track data lineage and provenance from source to consumption. Use when auditing data flows, debugging data quality issues, ensuring compliance (GDPR, SOX), or understanding data dependencies. Covers lineage tracking, impact analysis, data catalogs, and metadata management.

sunnypatneedi/claude-starter-kit · 56 tokens

multi-source-data-conflation

Merge and reconcile data from multiple sources into a unified view. Use when integrating APIs, consolidating databases, building data warehouses, or creating master data. Covers entity resolution, conflict resolution, data quality, and real-time vs batch conflation.

sunnypatneedi/claude-starter-kit · 57 tokens

software-architecture

Design scalable software systems with proven architectural patterns (MVC, microservices, event-driven), SOLID principles, system design trade-offs, and architectural decision records (ADRs).

sunnypatneedi/claude-starter-kit · 38 tokens