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/llama-farm/llamafarm/commit-push-prnpx skills add llama-farm/llamafarm --skill commit-push-prgit clone --depth 1 https://github.com/llama-farm/llamafarmWhat 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 | $0.00036 | $0.02340 |
| Opus 5 | $0.00018 | $0.01170 |
| Sonnet 5 | $0.00007 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
commit-push-pr scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Command injection (`shell=True`, `os.system`) | BLOCK | Cannot auto-fix - user must refactor | How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit, Push & PR Skill
Automates the git workflow of committing changes, pushing to GitHub, and opening a PR with intelligent handling of edge cases.
Required Reading
Before executing, internalize the git workflow standards: @.claude/rules/git_workflow.md
Key rules:
- Use Conventional Commits format:
type(scope): description - NEVER attribute Claude in commits or PRs (no co-author, no mentions)
- NEVER skip pre-commit hooks (no
--no-verify)
Execution Workflow
Step 1: Assess Git State
Run these commands to understand the current state:
# Detect the default branch (main, master, etc.)
DEFAULT_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@')
# Fallback if symbolic-ref fails (e.g., shallow clone or missing HEAD)
if [ -z "$DEFAULT_BRANCH" ]; then
DEFAULT_BRANCH=$(git remote show origin 2>/dev/null | grep 'HEAD branch' | awk '{print $NF}')
fi
# Final fallback to 'main' if detection fails
DEFAULT_BRANCH=${DEFAULT_BRANCH:-main}
# Get current branch
BRANCH=$(git branch --show-current)
# Check for uncommitted changes
git status --porcelain
# Check for unpushed commits (if branch has upstream)
git log origin/$DEFAULT_BRANCH..HEAD --oneline 2>/dev/null || echo "No upstream or no commits ahead"
# Check if branch has upstream tracking
git rev-parse --abbrev-ref @{upstream} 2>/dev/null || echo "No upstream"
Determine the state:
HAS_CHANGES: Are there uncommitted changes (staged, unstaged, or untracked)?HAS_UNPUSHED: Are there commits ahead of origin/$DEFAULT_BRANCH?ON_DEFAULT_BRANCH: Is current branch the default branch ($DEFAULT_BRANCH)?HAS_UPSTREAM: Does the branch track a remote?
Step 2: Handle "Nothing to Do" Case
If !HAS_CHANGES && !HAS_UNPUSHED:
Inform user: "No changes to commit and no unpushed commits. Nothing to do."
Exit gracefully.
Step 3: Handle "No Changes But Unpushed Commits" Case
If !HAS_CHANGES && HAS_UNPUSHED:
- Check if PR already exists:
gh pr list --head "$(git branch --show-current)" --json number,url,title
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.
- yesterday First seen · 337 lines · 36 tokens per session scan A afc4fb6d1a3a
commit-push-pr is a skill published in the GitHub repository llama-farm/llamafarm (837 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,340 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
frontend-unit-testing
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
gradio-themes
Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.
gradio
Build Gradio web UIs and demos in Python. Use when creating, modifying, debugging, or answering questions about Gradio and its capabilties, components, event listeners, or layouts.
hf-gradio
Use Gradio applications via API. Use when the user asks for to generate a prediction from a Gradio app on Hugging Face spaces or public URL. For example, "Generate an image using black-forest-labs/FLUX.2-dev".
analyzing-browser-forensics-with-hindsight
Parse Chromium-based browser databases with Hindsight to extract and correlate browsing history, downloads, cookies, cached content, autofill data, saved passwords, and extensions from Chrome, Edge, Brave, Opera, and Vivaldi into a unified timeline (XLSX, JSON, or SQLite output). Use during incident response…
hf-release-notes
Generate Hugging Face Hub (huggingfacehub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.