SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill gh-cligit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/gh-cli)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/gh-cli"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gh-cli/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/benchflow-ai/skillsbench/gh-cli"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gh-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01841 |
| Opus 5.5 | $0.00020 | $0.00736 |
| Sonnet 5.5 | $0.00010 | $0.00368 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
gh-cli 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skill-021 — 95% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI (gh)
Work seamlessly with GitHub from the command line.
Usage
gh <command> <subcommand> [flags]
Core Commands
issue: Manage issues
pr: Manage pull requests
repo: Create, clone, fork, and view repositories
api: Make an authenticated GitHub API request
run: View details about workflow runs
Use gh <command> --help for more information about a command.
gh pr
Work with GitHub pull requests.
USAGE
gh pr <command> [flags]
CORE COMMANDS
checkout: Check out a pull request in git
checks: Show CI status for a single pull request
close: Close a pull request
comment: Create a new pr comment
create: Create a pull request
diff: View changes in a pull request
edit: Edit a pull request
list: List and filter pull requests in this repository
merge: Merge a pull request
ready: Mark a pull request as ready for review
reopen: Reopen a pull request
review: Add a review to a pull request
status: Show status of relevant pull requests
view: View a pull request
FLAGS
-R, --repo [HOST/]OWNER/REPO Select another repository using the [HOST/]OWNER/REPO format
INHERITED FLAGS
--help Show help for command
ARGUMENTS
A pull request can be supplied as argument in any of the following formats:
- by number, e.g. "123";
- by URL, e.g. "https://github.com/OWNER/REPO/pull/123"; or
- by the name of its head branch, e.g. "patch-1" or "OWNER:patch-1".
EXAMPLES
$ gh pr checkout 353
$ gh pr create --fill
$ gh pr view --web
LEARN MORE
Use 'gh <command> <subcommand> --help' for more information about a command.
Read the manual at https://cli.github.com/manual
gh issue
Work with GitHub issues.
USAGE
gh issue <command> [flags]
CORE COMMANDS
close: Close issue
comment: Create a new issue comment
create: Create a new issue
delete: Delete issue
edit: Edit an issue
list: List and filter issues in this repository
reopen: Reopen issue
status: Show status of relevant issues
transfer: Transfer issue to another repository
view: View an issue
FLAGS
-R, --repo [HOST/]OWNER/REPO Select another repository using the [HOST/]OWNER/REPO format
INHERITED FLAGS
--help Show help for command
ARGUMENTS
An issue can be supplied as argument in any of the following formats:
- by number, e.g. "123"; or
- by URL, e.g. "https://github.com/OWNER/REPO/issues/123".
EXAMPLES
$ gh issue list
$ gh issue create --label bug
$ gh issue view --web
LEARN MORE
Use 'gh <command> <subcommand> --help' for more information about a command.
Read the manual at https://cli.github.com/manual
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 · 278 lines · 50 tokens per session scan A 94c4d99aa20c
gh-cli is a skill published in the GitHub repository benchflow-ai/skillsbench (1,855 stars, last pushed 6d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,841 once invoked, about $0.0002 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
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates the versions of all six published crates (drain included) in Cargo.toml files (exact patch version), version references in the backend middleware, hotpathinit skill, and README (major.minor only), and the relay workflow release tag pins…
parallel-pr-review
Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.
github
GitHub API integration via HTTP tool with automatic credential injection.
review-readiness
PR readiness dashboard — tracks which reviews have been completed per branch and gates merge decisions. Shows code review, tests, security, QA, and linting status.
project-setup
Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.
commit
Generate git commit messages from staged changes.