release-sidecar

release-sidecar is a skill for Claude Code from marcus/sidecar. It costs 53 tokens per session (1,474 once invoked), scanned A, original, MIT.

A release checklist for Sidecar software, covering versioning, dependencies, validation, automation, and package distribution.

In plain words
What is it for?
It helps prepare semantic-version tags, update Go dependencies and changelogs, run release automation, update Homebrew packages, and verify the release.
Why use it?
It turns the many checks involved in publishing a new version into a defined process.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/verify-release-archives.sh dist.

Good fit It helps prepare semantic-version tags, update Go dependencies and changelogs, run release automation, update Homebrew packages, and verify the release.

Compare 6 skills from other repositories ↓
About the project

Sidecar is a terminal-based workspace for running AI coding agents alongside file trees, task issues, Git diffs, and Jira or GitHub resources in split panes. Developers use it to monitor agent sessions, inspect files and changes, manage workspaces, and handle tasks without leaving one shell. The catalogue entries extend or guide coding-agent workflows used with Sidecar.

marcus/sidecar · 1,091 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/marcus/sidecar
agentmods
npx agentmods add skills/marcus/sidecar/release-sidecar

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-sidecar

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcus/sidecar/release-sidecar"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/release-sidecar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,474 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. 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 $0.00053 $0.01474
Opus 5.5 $0.00021 $0.00590
Sonnet 5.5 $0.00011 $0.00295
Haiku 4.5 $0.00005 $0.00147

Measured 1mo ago against content hash 163d347e89fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-sidecar 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 1mo 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-sidecar/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing a New Version

Operator contract: docs/guides/active/releasing.md. Enforcement lives in scripts/ and BUMP=minor make release (or RELEASE_VERSION=vX.Y.Z make release for an explicit version). Prefer the one-shot command over replaying this checklist by hand.

Prerequisites

  • Go matching go.mod
  • Clean working tree; main identical to live origin/main
  • Tests and Go CI green on the commit you will tag (tests and lint) — check-release-state.sh now checks this itself via gh run list --workflow=go-ci.yml and fails closed if it's red/running/missing, so you don't have to remember to look
  • GitHub CLI authenticated with push access to marcus/homebrew-tap
  • No replace directives in go.mod
  • HOMEBREW_TAP_TOKEN secret present in the GitHub repo (CI tap job)

Beware of go.work: always use GOWORK=off when updating dependencies and when validating install paths.

Local lint must match CI's golangci-lint v2.12.2, or trust CI:

gh run list --workflow=go-ci.yml --limit=1

Prepare (sidecar-specific)

1. Version

git tag -l 'v*' | sort -V | tail -1

SemVer: major / minor / patch as usual.

2. Sibling dependencies (td, tasks)

make sync-deps   # pins every github.com/marcus/* requirement to its latest tag

check-release-state.sh enforces this and refuses to tag when one is behind. go.work resolves those imports to the local checkouts, so drift is invisible locally — both the gate and sync-deps use GOWORK=off. If a sibling jumped several minors, decide deliberately (pin for a focused release vs take latest and note it under Dependencies) and smoke its tab in the app.

3. CHANGELOG

## [Unreleased]

### Features
- …

### Bug Fixes
- …

### Dependencies
- …

Commit the changelog (and any dependency bump) on main, then push so HEAD == origin/main. Leave the heading as ## [Unreleased] — make release stamps it to ## [vX.Y.Z] - YYYY-MM-DD for you.

Read the full file on GitHub · 157 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. 1mo ago Changed · +1 lines 163d347e89fe
  2. 1mo ago First seen · 156 lines · 53 tokens per session scan A 0d658cba8d98

Subscribe to this mod's changes

release-sidecar is a skill published in the GitHub repository marcus/sidecar (1,091 stars, last pushed 11d ago), licensed MIT. It adds 53 tokens to every session and 1,474 once invoked, about $0.0002 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 2026-08-30.