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 agentmods add skills/lovstudio/skills/gh-accessnpx skills add lovstudio/skills --skill gh-accessgit clone --depth 1 https://github.com/lovstudio/skillsWrote 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/lovstudio/skills/gh-access)<a href="https://agentmods.dev/skills/lovstudio/skills/gh-access"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/gh-access.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00151 | $0.02393 |
| Opus 5 | $0.00076 | $0.01196 |
| Sonnet 5 | $0.00030 | $0.00479 |
| Haiku 4.5 | $0.00015 | $0.00239 |
Grade A, and why
lov-gh-access 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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lov-gh-access
Grant, revoke, and audit collaborator access on private GitHub repos — by username or email, with read-only as the safe default.
Prerequisites
ghCLI authenticated (gh auth status) with a token that has:reposcope (always)admin:orgscope (if the target repo is org-owned; caller must be org owner or repo admin)
- The target repo exists and is accessible to the caller.
Subcommands
This skill has three modes. Pick based on the user's intent:
| User intent | Subcommand |
|---|---|
| "开权限 / share / invite / grant" | grant |
| "撤销 / remove / revoke / 踢出" | revoke |
| "谁有权限 / who has access / list" | list |
If intent is unclear, use AskUserQuestion to disambiguate.
Workflow
Step 0: Collect inputs via AskUserQuestion
ALWAYS collect the following BEFORE touching the API:
- Target repo —
<owner>/<repo>(e.g.skill-publisher/private-demo). If the user is inside a git repo, pre-fill fromgh repo view --json nameWithOwner -q .nameWithOwner. - Subcommand — grant / revoke / list.
- (grant/revoke only) Identifiers — a whitespace- or comma-separated list of GitHub usernames and/or email addresses. Mixed is fine.
- (grant only) Permission level — default
pull(read-only). Offer:pull— read + issues + PRs (recommended default)triage— read + can label/close issues & PRs, no code writepush— write access (⚠ confirm explicitly)maintain/admin— block unless user explicitly insists
Never silently escalate. If the user just says "给他权限" without specifying
level, default to pull and state that clearly.
Step 1: Resolve identifiers → GitHub usernames
For each identifier in the list, follow this resolution chain and record the outcome per identifier (for the final summary report):
identifier → classify → resolve
Classification rule: an identifier containing @ is treated as an email,
otherwise as a GitHub username.
Case A — looks like a username
What ships with it
5 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.
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.
- 4d ago First seen · 232 lines · 151 tokens per session scan A 3dc42b50d9de
lov-gh-access is a skill published in the GitHub repository lovstudio/skills (64 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 2,393 once invoked, about $0.0008 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.
Other skills, from other repositories
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
resolve-pr-comments
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
update-pr-summary
This skill should be used when user asks to "update PR summary", "update PR description", "rewrite PR body", "refresh PR title and body", or explicitly invokes "update-pr-summary".
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
tmux-ui-tripwire
Write or debug tmux-driven end-to-end TUI tests ("tripwires") for the ainb terminal app. Use when the user asks to "write a tmux test", "add a tripwire", "verify the TUI in tmux", "test feature X by pressing key Y", "validate plugin Z renders", or when editing any file under crates/ainb-core/tests/tripwire.rs.…
ainb-fleet:daemon
Long-running watcher that scans every claude session every 5s and auto-sends continue to any session whose recent tmux pane buffer matches a known API-error regex (ratelimited, overloadederror, internalservererror, requesttimeout, sockethangup, fetchfailed, ECONNRESET). Use this when you want unattended recovery from…