spec-as-source

A workflow where OpenSpec specification files are the source of truth and fenced Gherkin scenarios serve as executable acceptance tests. Gherkin is a plain-language format for describing expected software behavior.

In plain words
What is it for?
Use it when a project explicitly requires spec-first development, acceptance-test-first tasks, Gherkin specifications, or OpenSpec-based changes.
Why use it?
It keeps requirements, acceptance tests, and implementation aligned from the start.

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/intent-driven-dev/intent-driven-template/spec-as-source
Any agent
npx skills add intent-driven-dev/intent-driven-template --skill spec-as-source
Clone the repo
git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 632 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 $0.00036 $0.00632
Opus 5 $0.00018 $0.00316
Sonnet 5 $0.00007 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured yesterday against content hash ed399cfdbbf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-as-source 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/spec-as-source/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec As Source

Overview

Use OpenSpec spec.md files as the executable source of truth. When this skill is active, fenced-Gherkin authoring, acceptance-first task ordering, spec-first implementation, and BDD zone isolation are one workflow.

REQUIRED SUB-SKILL: Use gherkin-authoring when drafting or modifying fenced Gherkin.

REQUIRED SUB-SKILL: Use acceptance-test-authoring when configuring or modifying the acceptance runner, extractor, linting, step definitions, or page objects.

Activation

This workflow is opt-in. Apply it only when the user or project instructions explicitly require spec-as-source.

Once active, the BDD zone rules below are mandatory. Do not activate or disable zone isolation separately.

Artifact References

  • When this skill is active, its artifact references override the corresponding templates from the configured OpenSpec schema.
  • Draft each spec.md from references/spec.md, not from openspec/schemas/intent-driven/templates/spec.md.
  • Draft tasks.md from references/tasks.md, not from the schema task template, preserving acceptance-test-first ordering.

BDD Zone Rules

  1. Code is written only for an active change under openspec/changes/ whose scenarios describe the behavior.
  2. A unit of work edits either the specs zone (openspec/) or the code zone (everything else), never both while changes are uncommitted.
  3. Before crossing zones, finish and commit or stash the current zone.
  4. Never commit openspec/ files and code-zone files together.
  5. Any file named tasks.md is exempt and may be edited from either zone.
  6. Never revert or discard user-owned changes without explicit permission.

Use git status --porcelain before editing. Non-tasks.md paths under openspec/ select the specs zone; other changed paths select the code zone.

Workflow

  1. Draft and validate the proposal and fenced-Gherkin delta specs.
  2. Commit or stash specs-zone work before touching code.
  3. Establish the failing acceptance scenario or pending step before implementation.
  4. Implement the smallest change that makes the scenario pass.
  5. Keep the effective acceptance suite green with no pending or undefined steps.
  6. Commit or stash code-zone work before returning to specifications for sync or archive.

Read the full file on GitHub · 60 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 60 lines · 36 tokens per session scan A ed399cfdbbf1

Subscribe to this mod's changes

spec-as-source is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 632 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 2026-08-30.