ai-agent-session-center: Skill for Codex

.agents/skills/electron-release/SKILL.md

electron-release is a skill for Codex from coding-by-feng/ai-agent-session-center. It costs 49 tokens per session (1,016 once invoked), scanned A, original, MIT.

A release workflow for publishing a new macOS version of an Electron application for Apple computers using arm64 processors.

In plain words
What is it for?
Use it when explicitly releasing the next patch version of an Electron app through GitHub.
Why use it?
It organizes version changes, building, committing, pushing, and creating a public GitHub release while checking the repository state and release target.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is coding-by-feng/ai-agent-session-center's own configuration. It tells Codex how to work on ai-agent-session-center 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 ai-agent-session-center configures →

Reuse

Borrowing it

Nothing to install: this file belongs to coding-by-feng/ai-agent-session-center. 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/coding-by-feng/ai-agent-session-center/main/.agents/skills/electron-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/coding-by-feng/ai-agent-session-center

Made for: 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 electron-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/coding-by-feng/ai-agent-session-center/electron-release.svg)](https://agentmods.dev/skills/coding-by-feng/ai-agent-session-center/electron-release)
Your own site
<a href="https://agentmods.dev/skills/coding-by-feng/ai-agent-session-center/electron-release"><img src="https://agentmods.dev/badge/skills/coding-by-feng/ai-agent-session-center/electron-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,016 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 $0.00049 $0.01016
Opus 5 $0.00024 $0.00508
Sonnet 5 $0.00010 $0.00203
Haiku 4.5 $0.00005 $0.00102

Measured 8d ago against content hash 145b2be0525b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

electron-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 8d 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/electron-release/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Electron Build

Release the reviewed repository changes as the next patch version. This workflow changes version files, creates a commit, pushes it, and creates a public GitHub release, so keep every step scoped and verifiable.

Safety Rules

  • Treat explicit invocation or a direct release request as authorization for this release sequence, not for unrelated local files.
  • Inspect the worktree before changing it. Preserve unrelated edits and never use git add -A or git add ..
  • Exclude local-only state such as .codex/audit/, root-level generated bundles, screenshots, caches, credentials, and environment files.
  • Stop for user direction when a dirty file's inclusion is ambiguous or the current branch, remote, or release target is unexpected.
  • Never delete or overwrite a remote release, tag, or pushed commit as automatic error recovery.

1. Preflight

  1. Resolve the Git root and read the applicable AGENTS.md and CLAUDE.md.
  2. Inspect git status --short, the complete relevant diff, the current branch, its upstream, and the configured GitHub remote.
  3. Classify every changed and untracked file as release content, required version metadata, generated artifact, or unrelated local state. Record the exact paths intended for the commit.
  4. Verify GitHub CLI authentication with gh auth status.
  5. Refresh tags from the release remote and query the latest published release with gh release list. Do not rely only on potentially stale local tags.
  6. Confirm that the next patch version and its v<version> tag do not already exist locally or on GitHub.

2. Version

  1. Read the version from package.json.
  2. Run npm version patch --no-git-tag-version so package.json and an existing package-lock.json advance together.
  3. Verify the top-level versions match and inspect the version-file diff. Do not continue if the command changed dependencies or unrelated metadata.

3. Validate and Build

  1. Run npm run typecheck.
  2. Run targeted tests appropriate to the reviewed changes and any additional checks required by AGENTS.md.
  3. Run npm run electron:build. Diagnose failures and apply only narrow fixes that remain inside the approved release scope; rerun affected checks after a fix.
  4. Verify these non-empty artifacts for the new version:
    • dist/AI Agent Session Center-<version>-arm64.dmg
    • dist/AI Agent Session Center-<version>-arm64-mac.zip
  5. Compute SHA-256 checksums for both artifacts.

Read the full file on GitHub · 100 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. 8d ago First seen · 100 lines · 49 tokens per session scan A 145b2be0525b

Subscribe to this mod's changes

electron-release is a skill published in the GitHub repository coding-by-feng/ai-agent-session-center (82 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 1,016 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.

Related

Other skills, from other repositories

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…

GCWing/BitFun · 105 tokens

prepare-release

Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run /prepare-release.

CherryHQ/cherry-studio · 44 tokens

memstack-development-changelog-generator

Use when the user says 'generate changelog', 'update changelog', 'what changed', 'release notes', 'write changelog', or needs a formatted CHANGELOG.md from git commit history. Do NOT use for diary entries, git log viewing, or commit message writing.

cwinvestments/memstack · 63 tokens

release-notes-generator

Create release notes that summarize features, fixes, and migration guidance for software releases.

StanfordSpezi/SpeziVibe · 21 tokens

keep-a-changelog-generator

Generate changelog entries from git history using Keep a Changelog structure and user-facing release language.

StanfordSpezi/SpeziVibe · 25 tokens

auto-pr

Use when the user invokes /auto-pr or asks to "open N PRs against ", "auto-contribute to ", or "raise mergeable PRs automatically". Wraps the vouch auto-pr CLI: points at any github repo, learns its contribution norms (from shipped guidance, else synthesized from merged PRs), sources work items (open issues first…

vouchdev/vouch · 128 tokens