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/81120/light-agent/github_skillnpx skills add 81120/light-agent --skill github_skillgit clone --depth 1 https://github.com/81120/light-agentWhat 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 | $0.00030 | $0.00368 |
| Opus 5 | $0.00015 | $0.00184 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
github_skill 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 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.
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.
What it actually says
GitHub Skill
Use Cases
Use this skill to fetch the following from GitHub:
- Search trending repositories by language
- Query details for a specific repository
- Get stars, forks, descriptions, and related metadata
Steps
- Decide the query type (search or repository detail).
- Run
node scripts/github.js <command> [args]from this skill directory. - The script returns JSON output.
Commands
Search Trending Repositories
node scripts/github.js search <language> [limit]
language: language name, e.g.elixir,javascript,pythonlimit: number of results to return, default is 10
Get Repository Details
node scripts/github.js repo <owner>/<repo>
owner/repo: full repository name, e.g.phoenixframework/phoenix
Output Format
- Search: JSON array with repository name, description, stars, language, URL, etc.
- Repo detail: JSON object with full repository metadata
- Failure: error message
Examples
# Search trending Elixir repositories
node scripts/github.js search elixir 10
# Search trending JavaScript repositories
node scripts/github.js search javascript 5
# Get Phoenix repository details
node scripts/github.js repo phoenixframework/phoenix
Notes
- Uses GitHub public APIs with rate limits (60 requests/hour without auth)
- Authentication is not required for basic use
- You can configure a GitHub token in the script for higher quota
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.
- yesterday First seen · 65 lines · 30 tokens per session scan A ac388d7f55ba
github_skill is a skill published in the GitHub repository 81120/light-agent (24 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 368 once invoked, about $0.0002 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
study
Use when user wants to learn a new skill, technology, language, or topic. Use when user asks "teach me", "help me learn", "I want to study", "我想学", "教我", "学习路线", "从零开始学", "帮我学", "怎么学". Do not use for one-off factual questions, debugging help, or code review.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
publish-registry
Publish @agentos-software/ registry packages from AgentOS. Use whenever the user asks to publish or release registry software/agent packages.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.