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 skills add OpenMinis/MinisSkills --skill github-sync-helpergit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/github-sync-helper)<a href="https://agentmods.dev/skills/openminis/minisskills/github-sync-helper"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/github-sync-helper/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.
<a href="https://agentmods.dev/skills/openminis/minisskills/github-sync-helper"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/github-sync-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 YARA Match · line 6 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Tool Misuse · line 120 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 146 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.
- medium Excessive Agency · line 147 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.
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 | $0.00124 | $0.02941 |
| Opus 5.5 | $0.00050 | $0.01176 |
| Sonnet 5.5 | $0.00025 | $0.00588 |
| Haiku 4.5 | $0.00012 | $0.00294 |
Grade A, and why
github-sync-helper 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objectives
Codify GitHub/Git "basic operations" and common collaboration workflows into:
- A clear command quick reference (explanation + when to use)
- Executable one-click scripts (to avoid repetitive manual steps)
- Common outputs that are "numbered" whenever possible, so the user can reply with a number to choose an item directly, such as from a repository list
Security and Constraints (Must Be Followed)
| No. | Rule | Reason |
|---|---|---|
| 1 | Do not output tokens: No command may echo or print $GITHUB_TOKEN to stdout |
Prevent leaks |
| 2 | Require a second confirmation for dangerous operations: deleting branches, emptying directories, forced overwrites, force pushes, and direct pushes to main | These operations are hard to reverse |
| 3 | Use "branch + PR" collaboration by default; only "push directly to main" when the user explicitly requests it | Reduce the risk of damaging the main branch |
| 4 | Run git status before push/pull |
Prevent accidental commits or overwrites |
How to Run
- Script entry point:
sh /var/minis/skills/github-sync-helper/scripts/gh_sync.sh <command> [options]
The script runs in the "current Git repository directory" and must be run inside a repository.
Quick Reference for Basic Git/GitHub Operations (Explanation + Corresponding Script)
| No. | Category | Operation | One-sentence explanation | Common command | Script support |
|---|---|---|---|---|---|
| 1 | Initialize | init | Turn the current directory into a Git repository | git init |
init |
| 2 | Get code | clone | Download a repository from a remote to local | git clone <url> |
clone |
| 3 | Remote | remote | Manage remotes such as origin/upstream | git remote -v/add/set-url/remove |
remotes/add-remote/add-upstream/set-remote-url/remove-remote |
| 4 | Branch | branch | View, create, or delete branches | git branch -a/-d/-D |
branches/create-branch/delete-branches |
| 5 | Switch | checkout/switch | Switch to a branch | git switch <b> |
checkout |
| 6 | View changes | status/diff/log | View working tree changes, diffs, or history | git status git diff git log |
status/diff/log |
| 7 | Stage | add | Add changes to the staging area | git add -A |
add |
| 8 | Commit | commit | Package the staging area into a commit | git commit -m "..." |
commit |
| 9 | Sync | fetch/pull/push | Fetch, merge, or push commits | git fetch git pull git push |
fetch/pull/push/push-main |
| 10 | Merge | merge/rebase | Merge branch history | git merge git rebase |
merge/rebase (use with caution) |
| 11 | Stash | stash | Temporarily set aside uncommitted changes | git stash |
stash |
| 12 | Tag | tag | Add a version tag to a commit | git tag |
tag |
| 13 | Submodule | submodule | Manage subrepository dependencies | git submodule |
submodule |
| 15 | GitHub platform | issues/labels/milestones/releases/actions | Manage platform objects through the GitHub API | (API) | gh-issues-list and others (see below) |
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.
- 1mo ago First seen · 177 lines · 124 tokens per session scan A 775794c9d403
github-sync-helper is a skill published in the GitHub repository OpenMinis/MinisSkills (502 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 2,941 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
team-release
Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
testdino-releases
Use when the user wants to browse, inspect, create, or update releases/milestones in a TestDino project. Covers listreleases, getrelease, createrelease, and updaterelease. Accepts counter-style IDs like MS-12.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.