repo-publish

repo-publish is a skill for Claude Code, Codex from glebis/claude-skills. It costs 62 tokens per session (1,402 once invoked), scanned A, original, MIT.

A workflow for publishing a local code repository to a remote service, such as a Git hosting platform, with checks, version tags, commits, and deployment verification.

In plain words
What is it for?
It is for preparing commits, pushing repositories, creating releases, checking project quality, and verifying deployment.
Why use it?
It organizes the steps between finished local work and a reliable published release, while avoiding accidental handling of secrets.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for preparing commits, pushing repositories, creating releases, checking project quality, and verifying deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glebis/claude-skills/repo-publish
Install

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.

Any agent
npx skills add glebis/claude-skills --skill repo-publish
Clone the repo
git clone --depth 1 https://github.com/glebis/claude-skills

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 repo-publish

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/glebis/claude-skills/repo-publish"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/repo-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,402 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 91
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 127
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00062 $0.01402
Opus 5 $0.00031 $0.00701
Sonnet 5 $0.00012 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured 8d ago against content hash b550f6ce54c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-publish 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/intelligent_commit.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

repo-publish/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Publish

End-to-end pipeline for taking a project from "I made changes" to "live on a remote". Runs quality gates, generates an intelligent multi-commit history, pushes, and verifies the deploy.

When to Use

Use this skill when:

  • The user says "publish", "release", "ship it", "push to remote", "deploy this"
  • A project has accumulated local changes that need to land cleanly
  • A version bump or release needs to be cut
  • The user explicitly asks to run the full landing-the-plane workflow

Do not use this skill for:

  • Single quick commits the user is doing themselves
  • Documentation-only edits (use the project's own docs workflow)
  • Anything involving secrets/credentials (the scripts will skip those files)

Workflow Decision Tree

Start here. Pick the lane based on the user's intent:

User wants to publish
  ├─ Has local changes? ──── no ──► Just push / bump version
  ├─ Want a release? ──── yes ──► [Release mode](#release-mode)
  └─ Just routine commit? ──────► [Push mode](#push-mode)

Push Mode

For ordinary commits that need to land.

Step 1 — File remaining work

Run the issue tracker step:

bd ready              # What's pending
bd show <id>          # Inspect any blockers
bd update <id> --status in_progress  # Claim work

If you can't bd, ask the user how they track issues for this project. Don't silently skip it — issue hygiene is part of the gate.

Step 2 — Run quality gates

Inspect package.json, pyproject.toml, Makefile, or whatever exists and run whatever the project defines as "test + lint + build":

# Node
npm test && npm run lint && npm run build

# Python
pytest && ruff check . && mypy .

# Go
go test ./... && go vet ./...

# Rust
cargo test && cargo clippy -- -D warnings

# Makefile-driven
make test lint build

If a gate fails, stop. Report which gate failed and the relevant error. Don't try to fix the code in the same publish flow — open a fix-PR first.

For projects without an obvious test command, run ls to find the closest script and ask the user.

Read the full file on GitHub · 158 lines

Files

What ships with it

2 files 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 · 158 lines · 62 tokens per session scan A b550f6ce54c6

Subscribe to this mod's changes

repo-publish is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 1,402 once invoked, about $0.0003 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 2026-09-03.