speckit-companion: Skill for Claude Code

.claude/skills/submit-catalog-update/SKILL.md

submit-catalog-update is a skill for Claude Code from alfredoperez/speckit-companion. It costs 114 tokens per session (2,047 once invoked), scanned A, original, MIT.

A workflow for submitting a version update to the spec-kit community catalogue through a GitHub issue form. It uses the live form template and does not create a direct catalogue pull request.

In plain words
What is it for?
Use it to file a catalogue listing or version update for the companion extension after a minor or major release.
Why use it?
It follows the catalogue project's required submission process and avoids rejected update methods.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

This is alfredoperez/speckit-companion's own configuration. It tells Claude Code how to work on speckit-companion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything speckit-companion configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/alfredoperez/speckit-companion/main/.claude/skills/submit-catalog-update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alfredoperez/speckit-companion

Made for: Claude Code.

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 submit-catalog-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/alfredoperez/speckit-companion/submit-catalog-update/github.svg)](https://agentmods.dev/skills/alfredoperez/speckit-companion/submit-catalog-update)
Your own site
<a href="https://agentmods.dev/skills/alfredoperez/speckit-companion/submit-catalog-update"><img src="https://agentmods.dev/badge/skills/alfredoperez/speckit-companion/submit-catalog-update/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 submit-catalog-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/alfredoperez/speckit-companion/submit-catalog-update"><img src="https://agentmods.dev/badge/skills/alfredoperez/speckit-companion/submit-catalog-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00114 $0.02047
Opus 5 $0.00057 $0.01024
Sonnet 5 $0.00023 $0.00409
Haiku 4.5 $0.00011 $0.00205

Measured 12d ago against content hash a7143efd495c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

submit-catalog-update scanned grade A with 1 finding 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (render_submission.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(gh *), Bash(curl *), Bash(python3:*), Bash(git *), Bash(unzip *), Bash(mkdir *), Bash(uname *), Bash(specify *), Read
.claude/skills/submit-catalog-update/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Submit a community-catalog update

The catalog entry for companion is version-pinned, so a release only reaches catalog users once the entry is bumped. This files that bump.

Deliberately no Edit/Write: this skill writes to a third-party repository and must not be able to mutate ours.

Hard-won rules (do not skip)

  1. Never open a PR against extensions/catalog.community.json. github/spec-kit#3937 was closed unmerged — "Updates to extensions must use the extension submission issue template." The publishing guide is explicit: "Do not open a pull request directly to edit extensions/catalog.community.json." Both first listings and version updates go through the [Extension Submission] issue. If you find yourself typing gh pr create against github/spec-kit, you are in the wrong workflow.
  2. Never hardcode the ### headings. GitHub serializes an issue form as ### <label> / blank / value, and maintainers' validation parses that. render_submission.py fetches the live .github/ISSUE_TEMPLATE/extension_submission.yml and renders from its labels — including the (optional) suffixes. If it cannot fetch the template it aborts; it never falls back to a remembered shape, because that fallback is the failure this skill exists to prevent.
  3. The download URL is the version-pinned asset…/releases/download/speckit-ext-v$V/companion-$V.zip. Never companion-latest/companion.zip: the catalog requires the declared version to equal the downloaded bits. This issue body is the only place a pinned URL belongs, and it is generated into a scratch dir, never committed.
  4. Minor and major only. A patch does not touch the catalog; patch users ride companion-latest. Compare against the catalog's current pin, not against .0 — going 0.11.0 → 0.20.2 is a minor bump and correctly pins at the newest patch of the new line.
  5. Never rebuild the catalog JSON. The script deep-copies the live entry and applies deltas, because that entry carries verified, downloads, stars, and created_at which exist nowhere in extension.yml. Rebuilding drops them and reads as a destructive edit.
  6. Do not pass --label. We hold only pull on github/spec-kit; gh issue create --label errors for a user without triage rights and nothing gets filed. Maintainers apply extension-submission at triage — that is the documented flow.
  7. --body-file, never --body. The body carries em dashes, backticks, $, and fenced blocks.

Read the full file on GitHub · 81 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. 12d ago First seen · 81 lines · 114 tokens per session scan A a7143efd495c

Subscribe to this mod's changes

submit-catalog-update is a skill published in the GitHub repository alfredoperez/speckit-companion (90 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,047 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

deno-knowledge-patch

Use this skill when choosing current Deno runtime APIs, CLI options, configuration, dependency behavior, Node compatibility, or deployment workflows. Open the topic reference before changing a project because several commands, flags, APIs, and defaults changed more than once.

Nevaberry/nevaberry-plugins · 9 tokens

bun-knowledge-patch

Use this skill when working on Bun applications, packages, builds, tests, servers, or Node.js compatibility. Check the relevant reference before relying on older Bun behavior or translating Node-oriented code.

Nevaberry/nevaberry-plugins · 8 tokens

drizzle-knowledge-patch

Use this skill when work touches Drizzle SQL identifiers or aliases, Drizzle Kit module loading, or Zod schemas generated from Drizzle tables.

Nevaberry/nevaberry-plugins · 10 tokens

ts-debug

TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".

berekvolgyipeter/dotclaude · 68 tokens

typescript-pro

Implements advanced TypeScript type systems, creates custom type guards, utility types, and branded types, and configures tRPC for end-to-end type safety. Use when building TypeScript applications requiring advanced generics, conditional or mapped types, discriminated unions, monorepo setup, or full-stack type safety…

eric861129/SKILLS_All-in-one · 69 tokens

api-development

This skill should be used when implementing backend API services, file operations, and process management in TypeScript/Node.js.

Myst4ke/mcp-to-skills-converter · 26 tokens