A tool for managing GitHub repositories and reducing use of GitHub Actions, GitHub’s hosted automation system. It can audit workflows and move suitable checks to local hooks or a private server.

Use it to inspect workflow usage, adjust triggers and concurrency, add pre-push checks, set up a self-hosted runner on a VPS, publish commit statuses, and manage repository resources through GitHub’s CLI.

It helps identify workflows that consume cloud build minutes and limits accidental changes by backing up workflow files and using a separate branch.

sc-git — Skill for Claude Code by rahmanef63/si-coder-agent

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 rahmanef63/si-coder-agent --skill sc-git

Clone the repo

git clone --depth 1 https://github.com/rahmanef63/si-coder-agent

Made for: Claude Code.

Or install si-coder, the plugin that ships this one along with the rest of its 28 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rahmanef63/si-coder-agent/sc-git/github.svg)](https://agentmods.dev/skills/rahmanef63/si-coder-agent/sc-git)

Your own site

<a href="https://agentmods.dev/skills/rahmanef63/si-coder-agent/sc-git"><img src="https://agentmods.dev/badge/skills/rahmanef63/si-coder-agent/sc-git/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rahmanef63/si-coder-agent/sc-git"><img src="https://agentmods.dev/badge/skills/rahmanef63/si-coder-agent/sc-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,858 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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 medium

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 →

medium Excessive Agency · line 77
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 136
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00111	$0.02858
Opus 5.5	$0.00044	$0.01143
Sonnet 5.5	$0.00022	$0.00572
Haiku 4.5	$0.00011	$0.00286

Measured 1mo ago against content hash eec41eb6e629, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sc-git scanned grade A with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/_shared.js, scripts/audit.js, scripts/ci.js, …), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

6. **`gh` CLI, not raw curl**: reuse the existing `gh` auth + scopes. Fall back to `gh api` for endpoints without dedicated subcommands.

plugins/si-coder/skills/sc-git/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sc-git — GitHub Actions Replacement & Repo CRUD

Use when user wants to stop GitHub Actions cloud minutes burn, audit workflow files across your repos, migrate CI/CD to pre-push hooks + VPS, or do generic repo/workflow CRUD via gh API.

Connection-safe provider execution

Git/GitHub operations that need the selected SI-Coder GitHub credential should run through sc run -- ... when using a direct named connection. Credential-free local audits/CI helpers may run directly. Never export the PAT globally just to make a helper work.

Pre-requisites

gh CLI authed with repo + workflow + admin:repo_hook scopes
Local clones live in ~/projects/<repo> (override with PROJECTS_DIR) (some repos remote-only — skill handles both)
your VPS (set SC_GIT_VPS_HOST) accessible via SSH for runner/cron subcommands

CORE RULES

Never destructive without backup: before patching any .github/workflows/*.yml, copy to *.yml.bak. Never delete .bak files.
Never force-push, never push directly to main: all changes land via new branch chore/reduce-github-actions-usage. PR is user's call.
Never touch secrets / env / deploy targets: skill only edits triggers (on:), concurrency:, paths:. Leaves env:, secrets:, runs-on:, job steps alone unless explicitly told.
Never run failing workflows on cloud: when listing recent runs, do not retrigger.
Self-hosted runner only on private repos: GitHub strongly recommends. If all your active repos are private, this is safe. Refuse runner setup if target repo isPrivate === false.
gh CLI, not raw curl: reuse the existing gh auth + scopes. Fall back to gh api for endpoints without dedicated subcommands.
Idempotent: re-running disable on already-disabled workflow is a no-op (detect existing workflow_dispatch: only + no push:/pull_request:/schedule:).

Scripts

`audit.js` — Sweep + report

Scans all your repos, lists workflows, recent run volume, identifies burn risks.

Read the full file on GitHub · 195 lines

Files

What ships with it

11 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.

1mo ago Changed · +10 lines eec41eb6e629
1mo ago First seen · 185 lines · 111 tokens per session scan A c0a71d42eb9e

Subscribe to this mod's changes

sc-git is a skill published in the GitHub repository rahmanef63/si-coder-agent (13 stars, last pushed 3d ago), licensed MIT. It adds 111 tokens to every session and 2,858 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CI and CD Claude Code DevOps and cloud Git and workflow ai-agent claude-skills convex deployment-automation

bitbucket-workflow

Bitbucket best practices for pull requests, Pipelines CI/CD, Jira integration, and Atlassian ecosystem workflows.

Mindrally/skills · 27 tokens

gitlab-workflow

GitLab best practices for merge requests, CI/CD pipelines, issue tracking, and DevOps workflows.

Mindrally/skills · 24 tokens

pdlc-ship

A software release workflow that runs tests, updates the version and change log, creates a Git tag, and starts CI/CD, the automated build and deployment process.

kanfu-panda/pdlc-skills · 30 tokens

github-actions

Designs and hardens GitHub Actions CI/CD - pipelines that hit a sub-10-minute PR feedback budget through caching and parallelism, with least-privilege security and safe deploy gates. Use when someone asks "why is my CI so slow", "how do I cache nodemodules properly", "set up a deploy workflow", "is pullrequesttarget…

SkillMedev/skills · 139 tokens

check-dependabot

Validate a Dependabot configuration against the published JSON Schema and audit its groups against the repository's real dependency manifests. Use when creating or rewriting .github/dependabot.yml, when adding or reorganising groups, ignore or exclude-patterns, when a dependency lands in the wrong grouped PR or keeps…

sergeyklay/.agents · 163 tokens

monitor-ci

Drive a long-running GitHub Actions run to a trustworthy conclusion without burning the session on polling. Use when asked to wait for a pipeline, watch a build, babysit a release or deploy run, restart it if it fails, or report whether it went green. Also use when a run must finish before a follow-up step such as a…

sergeyklay/.agents · 181 tokens

sc-git