spec-apply

spec-apply is a command for coding agents from orlando-japan/claude-code-setting. It costs 9 tokens per session (250 once invoked), scanned A, original, MIT.

A workflow for carrying out tasks listed in an approved specification-change folder. It verifies each task as it is completed and updates the task checklist.

In plain words
What is it for?
Use it to implement tasks from openspec/changes, in their listed order, with verification after each one. It also handles logical commits and runs the full test suite when all tasks are checked.
Why use it?
It keeps implementation tied to the approved specification and catches discrepancies immediately. This prevents silently changing requirements when the specification is wrong.

Command

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 commands/orlando-japan/claude-code-setting/spec-apply
Clone the repo
git clone --depth 1 https://github.com/orlando-japan/claude-code-setting

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 spec-apply

README.md
[![agentmods](https://agentmods.dev/badge/commands/orlando-japan/claude-code-setting/spec-apply.svg)](https://agentmods.dev/commands/orlando-japan/claude-code-setting/spec-apply)
Your own site
<a href="https://agentmods.dev/commands/orlando-japan/claude-code-setting/spec-apply"><img src="https://agentmods.dev/badge/commands/orlando-japan/claude-code-setting/spec-apply.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 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 $0.00009 $0.00250
Opus 5 $0.00005 $0.00125
Sonnet 5 $0.00002 $0.00050
Haiku 4.5 $0.00001 $0.00025

Measured 4d ago against content hash 9796eb9b16e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-apply 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 4d 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.

templates/claude-user/commands/spec-apply.md · 19 lines

What it actually says

Execute the implementation tasks from the spec change folder: $ARGUMENTS (or the most recently modified folder under openspec/changes/ if no argument).

Rules:

  • Work tasks in the order listed in tasks.md.
  • For each task: read its verification line first. Know what "done" means before you start.
  • Run the verification immediately after implementing. Don't batch and verify at the end.
  • Check off tasks in tasks.md as they complete — edit the file, don't just claim it in chat.
  • If a task reveals the spec is wrong, stop. Don't silently fix the spec. Surface the discrepancy to the user and ask whether to update the spec before continuing.
  • Follow the four coding principles (think first, simple, surgical, goal-driven). Don't expand scope beyond what tasks specify.
  • Commit per logical task group, not per file. Reference the change slug in the commit message.

When all tasks are checked, run the full test suite and report. Don't run /spec:archive yourself — the user does that after review.

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. 4d ago First seen · 19 lines · 9 tokens per session scan A 9796eb9b16e4

Subscribe to this mod's changes

spec-apply is a command published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 250 once invoked, about $0.0000 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.