release

release is a skill for Claude Code, Codex from foru17/neko-master. It costs 47 tokens per session (716 once invoked), scanned A, original, MIT.

A release guide for publishing either the main product or its Go agent through Git tags. A Git tag is a named marker used to start a particular release build.

In plain words
What is it for?
Bumping the main product version, writing changelogs, documenting new environment variables, creating release tags, and checking release artifacts.
Why use it?
It prevents versioning, changelog, documentation, testing, and tag mistakes between the two release lines.

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/foru17/neko-master/release
Any agent
npx skills add foru17/neko-master --skill release
Clone the repo
git clone --depth 1 https://github.com/foru17/neko-master

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/foru17/neko-master/release.svg)](https://agentmods.dev/skills/foru17/neko-master/release)
Your own site
<a href="https://agentmods.dev/skills/foru17/neko-master/release"><img src="https://agentmods.dev/badge/skills/foru17/neko-master/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 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 $0.00047 $0.00716
Opus 5 $0.00023 $0.00358
Sonnet 5 $0.00009 $0.00143
Haiku 4.5 $0.00005 $0.00072

Measured 4d ago against content hash 0af9c609fcb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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.

.claude/skills/release/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Process

Two independent release lines, both driven entirely by git tags:

Line Tag CI workflow Artifact
Main product vX.Y.Z .github/workflows/docker-build.yml Multi-arch Docker image (Docker Hub + GHCR), ~20 min
Agent probe agent-vX.Y.Z .github/workflows/agent-release.yml Multi-arch agent binaries, ~1 min

agent-v* does not build Docker images. The agent binary version is injected at build time from the tag via ldflags — there is no version file to bump for the agent.

Main product release

  1. Version: bump version in the root package.json only (apps/* keep their own independent versions; the root field is the single source of truth).
  2. Changelog: add a dated section to BOTH CHANGELOG.md (Chinese) and CHANGELOG.en.md (English), Keep-a-Changelog style (## [X.Y.Z] - YYYY-MM-DD, ### 修复/Fixed, ### 优化/Changed). Link issue/PR numbers as reference-style links at the section end. Credit external contributors by handle.
  3. Env docs: any new environment variable must be documented in .env.example before release.
  4. Test gates (all must pass):
pnpm --filter @neko-master/collector exec tsc --noEmit
pnpm --filter @neko-master/collector test
pnpm --filter @neko-master/web exec tsc --noEmit
pnpm --filter @neko-master/web exec next build
  1. Ship:
git push origin main
git tag -a vX.Y.Z -m "<one-line summary>"
git push origin vX.Y.Z
gh release create vX.Y.Z --title "vX.Y.Z" --notes "<highlights + upgrade notes>"
  1. Verify CI: gh run list --limit 3 → the tag-branch "Build and Push Docker Image" run must end completed/success. Multi-arch builds can exceed 20 minutes; poll rather than assume.

Agent release

See docs/agent/release.en.md for full details. Short form:

cd apps/agent && go vet ./... && go test ./... && sh -n nekoagent && sh -n install.sh
git tag agent-vX.Y.Z && git push origin agent-vX.Y.Z

Keep AgentProtocolVersion (Go, internal/config/config.go) and the collector's minimum accepted protocol version in sync when the payload changes — the collector rejects too-old agents with HTTP 426.

Read the full file on GitHub · 58 lines

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 · 58 lines · 47 tokens per session scan A 0af9c609fcb0

Subscribe to this mod's changes

release is a skill published in the GitHub repository foru17/neko-master (3,861 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 716 once invoked, about $0.0002 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.