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.
npx agentmods add skills/stefanrows/claude-code-plugins/merge-to-mainnpx skills add stefanrows/claude-code-plugins --skill merge-to-maingit clone --depth 1 https://github.com/stefanrows/claude-code-pluginsWrote 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.
[](https://agentmods.dev/skills/stefanrows/claude-code-plugins/merge-to-main)<a href="https://agentmods.dev/skills/stefanrows/claude-code-plugins/merge-to-main"><img src="https://agentmods.dev/badge/skills/stefanrows/claude-code-plugins/merge-to-main.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.02140 |
| Opus 5 | $0.00022 | $0.01070 |
| Sonnet 5 | $0.00009 | $0.00428 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
merge-to-main 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge to Main Workflow
A fast, safe workflow for landing changes on main. Operating principles: scope once (detect tooling and the change set in a single pass, then reuse it), fail fast (cheap checks first), parallelize (independent checks run concurrently), skip what can't be affected (don't run checks the change set can't break), and one confirmation gate (batch everything the user must approve into a single question).
Setup
- Git auth: Use GitHub CLI (
gh auth setup-git) when available — avoid manual PAT or SSH configuration.
Phase 1 — Scope (one pass, drives everything after)
- Branch from fresh remote main without touching the local
maincheckout:git fetch origin && git switch -c <type>/<slug> origin/main. Use a conventional prefix (feat/,fix/,docs/,chore/,refactor/,test/). Always a fresh branch — never reuse one. - Detect tooling once. In one pass, read
package.json,pyproject.toml,Makefile,Dockerfile,docker-compose.yml,.github/workflows/, and any docs app (apps/docs,website/, Docusaurus, VitePress, OpenAPI spec, Storybook). Also checkProjectSettings/ProjectVersion.txt— its presence means this is a Unity project; note the exactm_EditorVersionit contains (reuse it verbatim in Phase 3, never guess or use "latest installed"), and also notePackages/manifest.json, any*.asmdef,.gitattributesLFS rules, and Unity CI config (GameCI or Unity Build Automation in.github/workflows/). IfProjectVersion.txtexists, readreferences/unity.mdbefore Phase 3. Note the exact lint/test/build/docs-build commands. Do not re-derive these later. - Compute the change set once:
git diff --name-only origin/main...HEAD(plus planned edits). From it, decide up front which checks apply:- Source code changed → lint + tests + build (+ container build if a Dockerfile exists and code/deps changed).
- Behavior that docs describe changed (APIs, CLI, config/env, UI flows, permissions, error codes) → matching doc pages must be updated in this branch.
- Docs-only change → skip tests/build/container; run only the docs build and link checks if the project has them.
- Lockfile/dependency-only change → tests + build + container; lint of unchanged source adds nothing.
- Unity —
Assets/**/*.cs,*.asmdef,Packages/manifest.jsonchanged → asset integrity + compile + EditMode tests. - Unity —
*.unity,*.prefab,*.asset,*.mat,*.controller(YAML) changed → asset integrity only, no compile needed. - Unity —
ProjectSettings/**changed → asset integrity + compile (build settings can break the player build). - Unity — art/audio/video binaries changed → asset integrity (LFS check) only.
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.
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.
- 4d ago First seen · 67 lines · 43 tokens per session scan A 31c6f17ed96f
merge-to-main is a skill published in the GitHub repository stefanrows/claude-code-plugins (3 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 2,140 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 2026-08-31.
Other skills, from other repositories
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog-entry
Add a new entry to CHANGELOG.yml under the current unreleased version (or create the version block if needed), then regenerate documentation. Use when the user says things like "add a changelog entry", "log this fix in the changelog", or "/changelog-entry".
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.