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/andrewbastin/gh-scout/exploring-githubnpx skills add AndrewBastin/gh-scout --skill exploring-githubgit clone --depth 1 https://github.com/AndrewBastin/gh-scoutWhat 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 | $0.00060 | $0.02702 |
| Opus 5 | $0.00030 | $0.01351 |
| Sonnet 5 | $0.00012 | $0.00540 |
| Haiku 4.5 | $0.00006 | $0.00270 |
Grade A, and why
exploring-github 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploring GitHub
Explore and understand GitHub repositories using the gh CLI — a zero-dependency alternative to MCP-based GitHub context servers like gitctx.
Prerequisites
ghCLI installed and authenticated- Works with any MCP client: Claude Code, Amp, Pi, or any agent with shell access
If gh is not found or not authenticated, stop and ask the user to install/authenticate it. If a command fails for a non-blocking reason (e.g., rate limit on a non-critical call), skip it and continue.
Context State
Maintain a mental "current repo" context. Once the user specifies a repo (e.g., rust-lang/rust), use -R owner/repo on all subsequent gh commands. Track:
- Repo:
OWNER/REPO— always pass via-R - Branch: default branch unless user switches — pass via
--branchor@refwhere applicable - Path prefix: for scoped file navigation
Tool Reference
1. Repository Discovery & Metadata
Find/search repos:
gh search repos "<query>" --sort stars --limit 10 --json fullName,description,stargazersCount,language,updatedAt
View repo metadata:
gh repo view OWNER/REPO --json name,description,defaultBranchRef,isPrivate,diskUsage,forkCount,stargazerCount,languages,homepageUrl
List branches:
gh api repos/OWNER/REPO/branches --paginate --jq '.[].name'
2. Code Navigation
List directory contents (root or subdir):
gh api repos/OWNER/REPO/contents/PATH --jq '.[] | "\(.type)\t\(.name)\t\(.size // "")"' -H "Accept: application/vnd.github.v3+json"
For a specific branch:
gh api "repos/OWNER/REPO/contents/PATH?ref=BRANCH" --jq '.[] | "\(.type)\t\(.name)\t\(.size // "")"'
Read a file:
gh api repos/OWNER/REPO/contents/PATH -H "Accept: application/vnd.github.v3.raw" 2>&1 | head -500
For a specific branch:
gh api "repos/OWNER/REPO/contents/PATH?ref=BRANCH" -H "Accept: application/vnd.github.v3.raw" 2>&1 | head -500
Read multiple files (run in parallel): Read each file with the command above. Run multiple Bash calls in parallel for efficiency.
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.
- 2d ago First seen · 265 lines · 60 tokens per session scan A cb4657a971dd
exploring-github is a skill published in the GitHub repository AndrewBastin/gh-scout (4 stars, last pushed 6mo ago), licensed MIT. It adds 60 tokens to every session and 2,702 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…