openspec-develop

openspec-develop is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 28 tokens per session (1,969 once invoked), scanned A, original, MIT.

An implementation tool for OpenSpec changes, where approved work is broken into tasks. It explores the project, completes the tasks, records progress, and stops at review checkpoints.

In plain words
What is it for?
Use it to work through an OpenSpec task list, update completed items, and pause when a defined approval gate is reached.
Why use it?
It turns an approved plan into a trackable implementation process instead of leaving task progress and completion status to manual memory.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; names the TodoWrite tool.

Part of the openspec plugin — 9 skills shipped together

Good fit Use it to work through an OpenSpec task list, update completed items, and pause when a defined approval gate is reached.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/openspec-develop
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 digital-stoic-org/agent-skills --skill openspec-develop
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install openspec, the plugin that ships this one along with the rest of its 9 skills.

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-develop

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-develop/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-develop)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-develop"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-develop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for openspec-develop

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-develop"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-develop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,969 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 4
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Excessive Agency · line 52
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00028 $0.01969
Opus 5.5 $0.00011 $0.00788
Sonnet 5.5 $0.00006 $0.00394
Haiku 4.5 $0.00003 $0.00197

Measured 1mo ago against content hash 6f585327452b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openspec-develop 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 1mo 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.

openspec/skills/openspec-develop/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Develop

Implementation engine for approved OpenSpec proposals. Turns tasks.md checkboxes into working code.

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

  1. Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."
  2. Present the options as a numbered text list and ask user to reply with their choice number.
  3. WAIT for user reply before continuing.

Workflow: Explore → Implement → Mark → Gate

flowchart LR
    A["Read task"] --> B["Explore context"]
    B --> C["Implement"]
    C --> D["Mark ✅ in tasks.md"]
    D --> E{"More tasks\nin section?"}
    E -->|Yes| A
    E -->|No| G{"Gate exists?"}
    G -->|No| H{"More sections?"}
    G -->|Yes| I["🚧 Checkpoint prompt"]
    I --> J["STOP"]
    H -->|Yes| A
    H -->|No| F["Report complete"]

    classDef action fill:#C8E6C9,stroke:#388E3C,color:#000
    classDef decision fill:#FFF9C4,stroke:#FBC02D,color:#000
    classDef gate fill:#FFE0B2,stroke:#F57C00,color:#000
    class A,B,C,D,F action
    class E,G,H decision
    class I,J gate

Critical: Mark checkbox immediately after each task. Enables crash recovery.

Guardrails

Autonomous (no confirmation needed):

  • Code generation matching specs
  • File edits within scope
  • Checkbox updates
  • Pattern-matching existing code

Ask-first (pause and confirm):

  • Architectural decisions not in specs
  • New dependencies not mentioned
  • Scope deviation >20% from proposal
  • Files outside change scope

Scope check: Before creating files not mentioned in proposal.md, count affected files. If >20% more than proposal's "Affected files", ask:

⚠️ Scope expansion detected
Proposal mentions: {n} files
Implementation needs: {m} files ({percent}% more)

Proceed with expanded scope? [y/N]

Read the full file on GitHub · 243 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. 1mo ago First seen · 243 lines · 28 tokens per session scan A 6f585327452b

Subscribe to this mod's changes

openspec-develop is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 28 tokens to every session and 1,969 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.

Related

Other skills, from other repositories