CORAL: Skill for Claude Code

.claude/skills/promoting-dev-to-main/SKILL.md

promoting-dev-to-main is a skill for Claude Code, Codex from Human-Agent-Society/CORAL. It costs 33 tokens per session (569 once invoked), scanned A, original, Apache-2.0.

A procedure for promoting a software release from a long-lived development branch into the main branch in GitHub.

In plain words
What is it for?
Use it to check the release pull request, review changes and checks, merge with a merge commit, and verify deployments and production checks.
Why use it?
It prevents the release history from being changed in ways that can cause repeated work or merge conflicts later.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present.

This is Human-Agent-Society/CORAL's own configuration. It tells Claude Code and Codex how to work on CORAL 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 CORAL configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Human-Agent-Society/CORAL. 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/Human-Agent-Society/CORAL/main/.claude/skills/promoting-dev-to-main/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Human-Agent-Society/CORAL

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 promoting-dev-to-main

README.md
[![agentmods](https://agentmods.dev/badge/skills/human-agent-society/coral/promoting-dev-to-main/github.svg)](https://agentmods.dev/skills/human-agent-society/coral/promoting-dev-to-main)
Your own site
<a href="https://agentmods.dev/skills/human-agent-society/coral/promoting-dev-to-main"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/promoting-dev-to-main/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 promoting-dev-to-main

Your own site · 80×15
<a href="https://agentmods.dev/skills/human-agent-society/coral/promoting-dev-to-main"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/promoting-dev-to-main.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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 $0.00033 $0.00569
Opus 5 $0.00016 $0.00284
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 12d ago against content hash c86ac311166b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

promoting-dev-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 12d 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/promoting-dev-to-main/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promoting dev to main

Core rule

Merge dev → main release PRs with a merge commit. Never squash or rebase these promotions.

Ordinary contribution PRs still target dev and may be squash-merged. The release promotion is the exception because main must retain dev in its ancestry. Squashing a promotion makes the next release re-present old commits and can create large false conflicts.

Workflow

  1. Confirm the PR is exactly base=main, head=dev and no duplicate release PR is open.

  2. Review main..dev, required CI, and deployment checks.

  3. In GitHub, open the merge-method dropdown and choose Create a merge commit. With the CLI, use:

    gh pr merge <number> --repo Human-Agent-Society/CORAL --merge
    
  4. Keep the long-lived dev branch. Do not delete or force-push it.

  5. Fetch both branches and verify the released dev tip is an ancestor of main:

    git fetch origin dev main
    git merge-base --is-ancestor origin/dev origin/main
    

    Exit status 0 is required.

  6. Confirm post-merge CI, release automation, deployments, and production smoke checks.

If GitHub reports conflicts

Do not force-rebase the shared dev branch. First inspect the topology and reproduce conflicts with git merge-tree.

If an earlier release was squash-merged, main may have the same tree as an earlier dev commit without sharing its ancestry. Verify tree equivalence before choosing a repair. Prefer merging main back into dev and pushing normally; use an ancestry-only ours merge only when exact tree equality proves main contains no unique content to preserve.

Red flags

  • GitHub's primary button says Squash and merge.
  • A command uses --squash, --rebase, or a force-push.
  • The release workflow proposes deleting dev.
  • Conflict resolution starts before checking commit topology and tree equality.

Stop when any red flag appears and return to the workflow above.

Quick reference

PR Allowed merge method
Feature/fix/docs branch → dev Repository default; usually squash
devmain release promotion Merge commit only

Read the full file on GitHub · 69 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. 12d ago First seen · 69 lines · 33 tokens per session scan A c86ac311166b

Subscribe to this mod's changes

promoting-dev-to-main is a skill published in the GitHub repository Human-Agent-Society/CORAL (975 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 569 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.