openspec-workflows

A workflow guide for OpenSpec, a system for writing, checking, and applying planned software changes. It explains when a change proposal is needed and lists the commands for viewing, validating, and archiving changes.

In plain words
What is it for?
Use it when creating a proposal, implementing a specification, or working with OpenSpec conventions. It covers preparation, naming change IDs, checking existing work, and validating proposals.
Why use it?
It helps agents decide whether work needs a formal proposal and follow the repository's required process. This keeps feature, breaking, architecture, performance, and security changes documented and checked.

Skill for Claude CodeCodexCursor

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/datenoio/iterabledata/openspec-workflows
Any agent
npx skills add datenoio/iterabledata --skill openspec-workflows
Clone the repo
git clone --depth 1 https://github.com/datenoio/iterabledata

Made for: Claude Code, Codex, Cursor.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 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 $0.00032 $0.00883
Opus 5 $0.00016 $0.00441
Sonnet 5 $0.00006 $0.00177
Haiku 4.5 $0.00003 $0.00088

Measured 3d ago against content hash b45e2e42c62d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openspec-workflows 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 3d 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.

.cursor/skills/openspec-workflows/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Workflows

When to Create Proposals

Create proposals for:

  • New features or capabilities
  • Breaking changes (API, schema)
  • Architecture changes
  • Performance optimizations (behavior changes)
  • Security pattern updates

Skip proposals for:

  • Bug fixes (restoring intended behavior)
  • Typos, formatting, comments
  • Non-breaking dependency updates
  • Configuration changes
  • Tests for existing behavior

Quick Commands

openspec list                  # List active changes
openspec list --specs          # List specifications
openspec show [item]           # Display change or spec
openspec validate [item] --strict  # Validate changes
openspec archive <change-id> --yes  # Archive after deployment

Creating Change Proposals

1. Context Checklist

Before starting:

  • Read openspec/project.md for conventions
  • Run openspec list to see active changes
  • Run openspec list --specs to see existing capabilities
  • Check for conflicts with pending changes

2. Choose Change ID

  • Use kebab-case, verb-led: add-, update-, remove-, refactor-
  • Examples: add-two-factor-auth, update-parquet-support
  • Ensure uniqueness

3. Scaffold Structure

mkdir -p openspec/changes/<change-id>/specs/<capability>

Create:

  • proposal.md - Why, what, impact
  • tasks.md - Implementation checklist
  • design.md - Only if needed (cross-cutting, architectural, or complex decisions)
  • specs/<capability>/spec.md - Delta changes

4. Write Spec Deltas

Use operation headers:

  • ## ADDED Requirements - New capabilities
  • ## MODIFIED Requirements - Changed behavior (include full requirement)
  • ## REMOVED Requirements - Deprecated features
  • ## RENAMED Requirements - Name changes

Critical: Every requirement MUST have at least one scenario:

#### Scenario: Success case
- **WHEN** user performs action
- **THEN** expected result

Read the full file on GitHub · 139 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. 3d ago First seen · 139 lines · 32 tokens per session scan A b45e2e42c62d

Subscribe to this mod's changes

openspec-workflows is a skill published in the GitHub repository datenoio/iterabledata (37 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 883 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.

Related

Other skills, from other repositories

fastapi

FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.

fastapi/fastapi · 57 tokens

breaking-change-report

Run the japicmp binary-compatibility report for wiremock-core and produce a filtered summary covering only @PublishedAPI-annotated classes. Use this when asked to generate, refresh, or summarise the breaking-changes report.

wiremock/wiremock · 50 tokens

geoserver-rest-api

Use when automating GeoServer management — programmatic workspace, datastore, and layer creation, style upload, service configuration via REST API. GeoServer REST API: manage GeoServer without GUI using curl, Python, or any HTTP client.

znlgis/opengis-skills · 53 tokens

create-or-update-pr

Create a pull request for the current branch, or update the existing one if it already exists. Regenerates the title (Conventional Commits format) and the body (Objective + What was done) from the actual changes, in English. INVOKE when the user asks to "open a PR", "create a PR", "update the PR", "update PR…

lukascivil/json-difference · 107 tokens

adhx

ADHX - X/Twitter Post Reader workflow skill. Use this skill when the user needs Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required and the operator…

diegosouzapw/awesome-omni-skills · 87 tokens

Data Analyzer

Statistical analysis and data transformation service for CSV and JSON datasets.

agenthatch/agenthatch · 16 tokens