Borrowing it
Nothing to install: this file belongs to alfredoperez/speckit-companion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfredoperez/speckit-companion/main/.claude/commands/publish-all.mdgit clone --depth 1 https://github.com/alfredoperez/speckit-companionWrote 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.
[](https://agentmods.dev/commands/alfredoperez/speckit-companion/publish-all)<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/publish-all"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/publish-all/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.
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/publish-all"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/publish-all.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.01972 |
| Opus 5.5 | $0.00012 | $0.00789 |
| Sonnet 5.5 | $0.00006 | $0.00394 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
publish-all 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Git status: !
git status --porcelain | head - Current branch: !
git branch --show-current - spec-kit ext version: !
grep -A4 '^extension:' apps/speckit-extension/extension.yml | grep 'version:' | tr -d ' "' | sed 's/version://' - VS Code ext version: !
node -p "require('./package.json').version" - Mod version: !
node -p "require('./apps/claude-mod/.claude-plugin/plugin.json').version" - Canvas version: !
node -p "require('./apps/copilot-canvas/plugin.json').version" - Latest
speckit-ext-v*tag: !git tag --list 'speckit-ext-v*' --sort=-version:refname | head -1 - Latest
v*tag: !git tag --list 'v*' --sort=-version:refname | head -1 - Latest
speckit-companion--v*tag: !git tag --list 'speckit-companion--v*' --sort=-version:refname | head -1 - Latest
canvas-v*tag: !git tag --list 'canvas-v*' --sort=-version:refname | head -1
Your task
Release every deliverable in one pass. This command only orchestrates: each phase's steps live in its own command, which stays the single source of truth.
| Phase | Deliverable | Command | Tag | Where it lands |
|---|---|---|---|---|
| 1 | spec-kit extension | .claude/commands/publish-speckit-ext.md |
speckit-ext-v* |
GitHub release, companion-latest |
| 2 | VS Code extension | .claude/commands/publish.md |
v* |
Marketplace, through release.yml |
| 3 | Claude Code mod | .claude/commands/publish-mod.md |
speckit-companion--v* |
this repo's plugin marketplace |
| 4 | Copilot canvas | .claude/commands/publish-canvas.md |
canvas-v* |
external plugin listing on github/awesome-copilot |
The spec-kit extension goes before the VS Code extension, always. The .vsix bundles apps/speckit-extension/extension.yml and compares it with the version installed in a user's project to say their spec-kit commands are out of date. Packaging the VS Code extension before the spec-kit bump ships a .vsix that expects the old version, so nobody hears about the new one until the next VS Code release. Packaging it against a version companion-latest does not serve yet tells every user to update to something the download does not have.
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.
- 11d ago Changed 6b258ea4b6b7
- 21d ago First seen · 74 lines · 30 tokens per session scan A 61f3b49d8ad3
publish-all is a command published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 1,972 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 2026-10-04.
Other commands, from other repositories
release
Prepare and publish spec-driven-steroids through the tag-triggered npm release pipeline.
ia-changelog
Create engaging changelogs for recent merges to main branch.
ship
Ship: review gate, tests, version bump, changelog, conventional commit, docs update, PR. Complete pipeline from done to merged.
repo-sprint
Collection health triage and work-session kickoff (dirty, unpushed, active, release candidates, audit gaps, stale, unpublished).
run-release
Orchestrate a tagged release using the release workflow.
bump
Bump the app version or build number across all targets in the current project.