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 instructions/zveinn/git-feed/claude-mdgit clone --depth 1 https://github.com/zveinn/git-feedWhat 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 | $0.05737 | $0.05737 |
| Opus 5 | $0.02868 | $0.02868 |
| Sonnet 5 | $0.01147 | $0.01147 |
| Haiku 4.5 | $0.00574 | $0.00574 |
Grade A, and why
git-feed CLAUDE.md 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
GitHub Feed is a Go CLI tool for monitoring GitHub pull requests and issues across repositories. It tracks contributions, reviews, and assignments with colorized output and real-time progress visualization.
The tool is also called "GitAI" in the README (branding name), but the binary is github-feed.
Build & Run
# Build the binary
go build -o github-feed .
# Run directly (fetches from GitHub API)
./github-feed
# Run with flags
./github-feed --time 3h # Show items from last 3 hours
./github-feed --time 2d # Show items from last 2 days
./github-feed --time 3w # Show items from last 3 weeks
./github-feed --time 6m # Show items from last 6 months (default: 1m)
./github-feed --time 1y # Show items from last year
./github-feed --debug # Show detailed API logging instead of progress bar
./github-feed --local # Use local database instead of GitHub API (offline mode)
./github-feed --links # Show hyperlinks underneath each PR/issue
./github-feed --ll # Shortcut for --local --links (offline mode with links)
./github-feed --clean # Delete and recreate the database cache
./github-feed --allowed-repos="owner/repo1,owner/repo2" # Filter to specific repos
Configuration
The tool requires a GitHub Personal Access Token with repo and read:org scopes (not needed in --local mode). Configuration is loaded from:
- Environment variables:
GITHUB_TOKENorGITHUB_ACTIVITY_TOKEN, andGITHUB_USERNAMEorGITHUB_USER - Config file at
~/.github-feed/.env(automatically created on first run)
Database location: ~/.github-feed/github.db (automatically created on first run)
First Run: The tool automatically creates ~/.github-feed/ directory with:
.envfile with template for credentials (permissions: 0600)github.dbdatabase for caching GitHub data (permissions: 0666)- Directory permissions: 0755
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 · 399 lines · 5,737 tokens per session scan A 3c91b390837c
git-feed CLAUDE.md is an instructions file published in the GitHub repository zveinn/git-feed (10 stars, last pushed 2mo ago), licensed MIT. It adds 5,737 tokens to every session, about $0.0287 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.