claude-context: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code from lbruton/claude-context. It costs 27 tokens per session (3,536 once invoked), scanned A, original, MIT.

A release workflow for versioned software. It coordinates version changes, a separate Git worktree, commits, a pull request, and a GitHub Release, while allowing project-specific release rules.

In plain words
What is it for?
Use `patch` for a small version increment, `release` for a larger shipped change, or `dry-run` to preview the work. It also gathers the project's identity and delegates file edits to project-specific rules when available.
Why use it?
Release steps often touch several files and repository operations that are easy to perform inconsistently. This workflow provides one sequence for patch updates and larger releases, with a dry-run option.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents); mentions Codex.

This is lbruton/claude-context's own configuration. It tells Claude Code how to work on claude-context 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 claude-context configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lbruton/claude-context. 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/lbruton/claude-context/master/.agents/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lbruton/claude-context

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lbruton/claude-context/release"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,536 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 $0.00027 $0.03536
Opus 5.5 $0.00011 $0.01414
Sonnet 5.5 $0.00005 $0.00707
Haiku 4.5 $0.00003 $0.00354

Measured 5d ago against content hash 080205824acb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 5d 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.

.agents/skills/release/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release — Universal Version Lock Workflow

Project-agnostic release orchestrator. Handles the version lock protocol, worktree lifecycle, PR creation, and GitHub Release. Delegates the actual file edits (Phase 1) to the project-level release/SKILL.md if one exists — otherwise uses sensible defaults.

When to Run

patch — bump PATCH number after every meaningful committed change. Default dev workflow. release — bump RELEASE/MINOR number when shipping a major batch to main.

Arguments

$ARGUMENTS can be:

  • release — bump RELEASE number (e.g., 3.23.01 → 3.24.00, or 0.2.3 → 0.3.0)
  • patch — bump PATCH number (e.g., 3.23.01 → 3.23.02, or 0.2.3 → 0.2.4)
  • dry-run — preview all changes without writing
  • If no argument provided, ask the user whether this is a release or patch.

Phase 0: Gather Context

Step 0.0: Read Project Identity

Use the Read tool on .claude/project.json.

Extract name, tag, issuePrefix. These are used throughout:

  • issuePrefix → issue references in commits and PRs (e.g., STAK-55, FORGE-82)
  • plane.projectId → Plane issue lookups (mcp__plane__*)
  • tag → used in commit messages and lock file entries

Determine the PR target branch:

  • If the repo has a dev branch: patches PR to dev, releases ship dev → main
  • If no dev branch: patches PR to main directly
git branch -a | grep -q 'remotes/origin/dev' && echo "TARGET=dev" || echo "TARGET=main"

Step 0.1: Remote Sync Gate (HARD GATE)

Before claiming a version lock or creating a worktree, ensure local branch matches remote.

git fetch origin
TARGET_BRANCH=$(git branch -a | grep -q 'remotes/origin/dev' && echo dev || echo main)
BEHIND=$(git rev-list HEAD..origin/$TARGET_BRANCH --count)

If BEHIND is 0: Continue. If BEHIND > 0: HARD STOP.

Local $TARGET_BRANCH is N commits behind origin/$TARGET_BRANCH.
Run: git pull origin $TARGET_BRANCH
Then re-run /release patch.

Step 0.2: Version Lock Claim (REQUIRED)

Read the full file on GitHub · 449 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. 5d ago Changed 080205824acb
  2. 9d ago Changed · +9 lines 4a639b5f51a5
  3. 11d ago First seen · 440 lines · 27 tokens per session scan A edc8e37eaea0

Subscribe to this mod's changes

release is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 3,536 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 2026-10-17.