openspec

openspec is a skill for Claude Code, Codex from saski/arnesto. It costs 55 tokens per session (1,349 once invoked), scanned A, original, Unlicense.

A specification-driven development workflow that records proposed changes, requirements, and decisions before and during implementation. It is intended for features, migrations, refactors, and bug fixes.

In plain words
What is it for?
Use it to prepare change proposals, write delta specifications, and maintain an implementation trail across sessions.
Why use it?
It gives teams a durable, reviewable description of intended behavior, reducing ambiguity and preserving the reasoning behind multi-step engineering work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it to prepare change proposals, write delta specifications, and maintain an implementation trail across sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saski/arnesto/openspec
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.

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

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for openspec

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/openspec.svg)](https://agentmods.dev/skills/saski/arnesto/openspec)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/openspec"><img src="https://agentmods.dev/badge/skills/saski/arnesto/openspec.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00055 $0.01349
Opus 5 $0.00028 $0.00674
Sonnet 5 $0.00011 $0.00270
Haiku 4.5 $0.00006 $0.00135

Measured 3d ago against content hash 025d1213d6e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

openspec 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.

.agents/skills/openspec/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec

Use OpenSpec as the planning layer when work needs durable requirements, reviewable intent, or a multi-session implementation trail. Keep the repository's normal engineering rules active: start implementation with tests where applicable, work in small steps, and run the project's canonical checks.

Before You Start

  1. Check whether the current repository already has an openspec/ directory or docs/openspec/.
  2. Resolve and verify the CLI with the NVM-aware procedure below.
  3. If OpenSpec is missing and the user asked to adopt it, initialize it with the shared installer after confirming the target repository.
  4. If OpenSpec is present, read the relevant openspec/specs/*/spec.md and active openspec/changes/<change>/ artifacts before proposing edits. If openspec/ is a symlink to docs/openspec/, keep using openspec/... paths for CLI compatibility while recognizing that the physical files live under docs/openspec/.
  5. Treat OpenSpec artifacts as source files: update them with the same care as code, keep language precise, and include them in validation.

CLI Runtime Resolution

Non-interactive clients such as Codex App may not inherit the shell that loads NVM. On this machine OpenSpec is managed by the NVM default Node installation; the exact Node version is intentionally not hard-coded. Before reporting a missing CLI, use this resolution sequence:

if ! openspec --version >/dev/null 2>&1; then
    if [ -s "$HOME/.nvm/nvm.sh" ]; then
        . "$HOME/.nvm/nvm.sh"
    fi
fi
openspec --version

Do not conclude that OpenSpec is unavailable merely because it is absent from the initial PATH, or because ~/.agents/bin/openspec reports env: node: No such file or directory. Load NVM and retry first. Only treat it as missing when the post-NVM openspec --version still fails.

Shared Installer

This tooling repo exposes a portable installer through the shared ~/.agents symlink:

~/.agents/skills/openspec/scripts/install-openspec
~/.agents/skills/openspec/scripts/install-openspec /path/to/repo

Read the full file on GitHub · 131 lines

Files

What ships with it

1 file 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. 3d ago First seen · 131 lines · 55 tokens per session scan A 025d1213d6e1

Subscribe to this mod's changes

openspec is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 55 tokens to every session and 1,349 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 2026-09-03.