spec-workflow

A set of rules for a software design document, or SDD, workflow. It classifies planned changes by risk and defines which specification sections, task plans, approvals, and folders each class requires.

In plain words
What is it for?
Use it when planning features or changes to decide whether they need a full, lightweight, or no specification. It also defines required artifacts for each level.
Why use it?
It prevents risky work from starting with too little planning and gives the team a consistent checkpoint before implementation.

Cursor rule for Cursor

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 rules/gosha70/code-copilot-team/spec-workflow
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Cursor.

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 1,113 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 $0.00025 $0.01113
Opus 5 $0.00013 $0.00557
Sonnet 5 $0.00005 $0.00223
Haiku 4.5 $0.00003 $0.00111

Measured yesterday against content hash 16948212de92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-workflow 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.

adapters/cursor/.cursor/rules/spec-workflow.mdc · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Workflow — SDD Specification Protocol

Rules governing when a Software Design Document (SDD) spec is required, what sections it must contain, and how it gates the transition from Plan to Build.

Risk-Based spec_mode Classification

Every planned feature is assigned a spec_mode based on change risk. The Plan agent determines this value and records it in specs/<feature-id>/plan.md YAML frontmatter.

spec_mode When to use
full Security changes, schema changes, integration work, features touching more than 2 files
lightweight Features touching 1–2 files, non-critical changes
none Bug fixes (non-security), docs-only changes, trivial or cosmetic changes

When in doubt, escalate to the next higher mode. Under-speccing a risky change costs more than over-speccing a safe one.

Required Spec Sections per Mode

full

All sections from spec-template.md are required, plus a tasks.md task breakdown:

  • User Scenarios
  • Requirements
  • Constraints / What NOT to Build
  • Key Entities
  • Success Criteria
  • tasks.md — discrete, bounded build tasks derived from the spec

lightweight

Only two sections are required in spec.md:

  • Requirements
  • Constraints

none

No spec.md is required. The Plan agent writes only plan.md.

Plan Approval Gate Protocol

What the Plan Agent Writes

The Plan agent always writes specs/<feature-id>/plan.md regardless of spec_mode. The file must include YAML frontmatter with at minimum:

---
feature_id: <feature-id>
spec_mode: full | lightweight | none
status: draft | approved
origin:
  # at least one of: issue, urls, transcripts — OR the explicit
  # internal/unrecoverable exemption. See origin-confirmation skill.
  issue: <repo>#<number>
  urls:
    - <external-reference-url>
  transcripts:
    - specs/<feature-id>/origin/<date>-<slug>.md
  origin_claim: |
    One paragraph in the user's words quoting their original ask.
---

Read the full file on GitHub · 121 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 · 121 lines · 25 tokens per session scan A 16948212de92

Subscribe to this mod's changes

spec-workflow is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,113 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 2026-08-31.