speckit-self

A maintenance command for the Specify command-line tool used by Spec Kit, a toolkit for planning software through written specifications.

In plain words
What is it for?
Use it to check for a newer release, preview an upgrade, upgrade normally, or install a specific pinned version.
Why use it?
It helps you find available updates and preview or apply an upgrade to the tool itself.

Skill for Claude CodeCodex

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/github/spec-kit-copilot/speckit-self
Any agent
npx skills add github/spec-kit-copilot --skill speckit-self
Clone the repo
git clone --depth 1 https://github.com/github/spec-kit-copilot

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 353 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 $0.00084 $0.00353
Opus 5 $0.00042 $0.00177
Sonnet 5 $0.00017 $0.00071
Haiku 4.5 $0.00008 $0.00035

Measured 2d ago against content hash 3ae409f36ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit-self 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 2d 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.

skills/speckit-self/SKILL.md · 42 lines

What it actually says

Spec Kit — self (CLI maintenance)

Maintain the Specify CLI itself with the specify self command group.

Prerequisite: needs the specify CLI. If specify --version fails, install it with the speckit-cli-setup skill first.

When to use

  • The user asks whether a newer specify-cli release exists.
  • The user wants to upgrade the CLI, or preview what an upgrade would do.

How to invoke

# Read-only: is a newer release available?
specify self check

# Preview the upgrade without changing anything
specify self upgrade --dry-run

# Upgrade in place
specify self upgrade

# Upgrade to a specific pinned release
specify self upgrade --tag <version>

Notes

  • specify self check is read-only and safe.
  • Run specify self upgrade --dry-run first and show the user the preview before performing an actual in-place upgrade.
  • After upgrading, run specify version (see the speckit-check skill) to confirm the new version.
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. 2d ago First seen · 42 lines · 84 tokens per session scan A 3ae409f36ef4

Subscribe to this mod's changes

speckit-self is a skill published in the GitHub repository github/spec-kit-copilot (11 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 353 once invoked, about $0.0004 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.