talos-mcp-server: Skill for Claude Code

.claude/skills/release-preflight/SKILL.md

release-preflight is a skill for Claude Code from Nosmoht/talos-mcp-server. It costs 64 tokens per session (980 once invoked), scanned A, original, MIT.

A release-readiness check for the Talos MCP project before creating and pushing a version tag. A version tag is a Git label that starts a release process.

In plain words
What is it for?
Run it before a v-tag to review commits, determine the expected major, minor, or patch change, check the release build, and verify npm’s OIDC and provenance settings.
Why use it?
It detects unsuitable commit ranges, inconsistent version-bump expectations, failed GoReleaser checks, and incorrect npm publishing settings before release.

Skill for Claude Code

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

This is Nosmoht/talos-mcp-server's own configuration. It tells Claude Code how to work on talos-mcp-server 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 talos-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nosmoht/talos-mcp-server. 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/Nosmoht/talos-mcp-server/main/.claude/skills/release-preflight/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Nosmoht/talos-mcp-server

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 release-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/release-preflight/github.svg)](https://agentmods.dev/skills/nosmoht/talos-mcp-server/release-preflight)
Your own site
<a href="https://agentmods.dev/skills/nosmoht/talos-mcp-server/release-preflight"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/release-preflight/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 release-preflight

Your own site · 80×15
<a href="https://agentmods.dev/skills/nosmoht/talos-mcp-server/release-preflight"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/release-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 980 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.
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 $0.00064 $0.00980
Opus 5 $0.00032 $0.00490
Sonnet 5 $0.00013 $0.00196
Haiku 4.5 $0.00006 $0.00098

Measured 9d ago against content hash 0216139459a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-preflight 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 9d 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.

.claude/skills/release-preflight/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Preflight

Validate release readiness before a v* tag is pushed. Fails closed — any blocker yields NO-GO and the skill never instructs the user to push on NO-GO.

Arguments

Parse $ARGUMENTS:

  • --from <tag> — base tag. If absent, resolve via:
    git describe --tags --abbrev=0 --match 'v*'
    
    If no prior v* tag exists and --from was not supplied, abort: NO-GO: no prior v* tag and --from not supplied.

Bind the resolved value as PREV.

Key Steps

  1. Resolve the release range. Scan commits that touched server paths (release triggers per CLAUDE.md § Release):

    git log "$PREV"..HEAD --pretty=format:'%s%n%b' \
      -- cmd internal go.mod go.sum Makefile
    

    If the filtered result is empty, abort: NO-GO: range contains only docs/ci/chore changes — do not tag.

  2. Derive expected bump. Apply this mapping to the filtered commit subjects, take the highest bump seen:

    Prefix Bump
    feat!: / BREAKING CHANGE: in body major
    feat: minor
    fix: patch
    docs: / ci: / chore: / build: none

    Confirm with the user via AskUserQuestion (header Bump): computed bump as the recommended option, plus alternatives and Cancel. CancelNO-GO.

  3. Goreleaser.

    command -v goreleaser >/dev/null || blocker "goreleaser not installed"
    goreleaser check                 || blocker "goreleaser check failed"
    
  4. release.yml invariants. Verify .github/workflows/release.yml exists (blocker if not), then apply the checks from references/release-checks.md:

    • node-version: "24" (not 22, not 20)
    • no registry-url: set on actions/setup-node
    • --provenance present on every npm publish call Each mismatch is a blocker; continue running remaining checks to build a complete report.

Read the full file on GitHub · 99 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. 9d ago First seen · 99 lines · 64 tokens per session scan A 0216139459a0

Subscribe to this mod's changes

release-preflight is a skill published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 980 once invoked, about $0.0003 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.