agentmods.dev

gh-watch: Instructions file for Claude Code

CLAUDE.md

gh-watch CLAUDE.md is an instructions file for Claude Code from justincampbell/gh-watch. It costs 688 tokens per session, scanned A, original, MIT.

Project instructions for gh-watch, a Go command-line tool that watches GitHub pull requests, commits, branches, and tags for changes.

In plain words
What is it for?
Use them when modifying gh-watch or working on its GitHub queries, state comparisons, event reporting, polling, or tests.
Why use it?
They give a coding agent the repository's architecture, design decisions, development practices, and testing context before it edits the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is justincampbell/gh-watch's own configuration. It tells Claude Code how to work on gh-watch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gh-watch configures →

not rated 4repo 20d ago A scan 688 tokens original MIT
View source ↗ justincampbell/gh-watch
Reuse

Borrowing it

Nothing to install: this file belongs to justincampbell/gh-watch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/justincampbell/gh-watch/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/justincampbell/gh-watch

Made for: Claude Code.

Wrote 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.

agentmods badge for gh-watch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/justincampbell/gh-watch/claude-md.svg)](https://agentmods.dev/instructions/justincampbell/gh-watch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/justincampbell/gh-watch/claude-md"><img src="https://agentmods.dev/badge/instructions/justincampbell/gh-watch/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 688 This file is loaded in full into every session.
When invoked 688 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00688 $0.00688
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 8d ago against content hash 6f8559bed5fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gh-watch 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 8d 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.

CLAUDE.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gh-watch

A gh CLI extension that watches GitHub resources for state changes. See README.md for usage, flags, event types, and output format.

Architecture

  • main.go — CLI entry point (cobra). Root command + pr, commit, branch, and tag subcommands.
  • internal/checks/ — Shared CheckRun type, CI summary helpers, and StatusContext mappers used by both PR and commit.
  • internal/pr/ — PR state snapshot types and GraphQL fetcher (via go-gh SDK).
  • internal/commit/ — Commit CI state snapshot types and GraphQL fetcher.
  • internal/branch/ — Branch head-commit snapshot types and GraphQL fetcher.
  • internal/tag/ — Tag list snapshot types and fetcher. Lists tags via GraphQL; for --contains, resolves ancestry via the REST compare API (api.DefaultRESTClient) — the only REST usage in the repo — memoized per tag SHA.
  • internal/events/ — Event types and diffing logic. ci.go has shared CI diff logic; diff.go adds PR-specific events (reviews, comments, merge conflicts); commit_diff.go handles commit initial state; branch_diff.go emits new-commit; tag_diff.go emits tag-created.
  • internal/poller/ — Generic poller using Go generics (Config[S any]). Pluggable strategy interface (currently FixedStrategy). Wraps Fetch in cenkalti/backoff/v5 to retry transient errors (default 30min budget per poll, so a watch outlives a GitHub incident).
  • internal/retry/ — Classifies API errors as transient (IsTransient): GitHub 5xx/429, secondary rate limits (403 + Retry-After, surfaced via RetryAfter), GraphQL INTERNAL errors returned with HTTP 200, network errors, timeouts, and malformed bodies.
  • internal/output/ — JSON to stdout.
  • plugin/ — Claude Code plugin: provides skills for monitoring PRs, commits, branches, and tags.

Key design decisions

  • Named gh-watch (not gh-watch-pr) to support future subcommands like gh watch commit, gh watch branch.
  • Poller uses generics so it's reusable for future watch targets beyond PRs.
  • Only aggregate CI events are emitted (ci-passed, ci-failed) — individual check transitions are noise.
  • Dependencies: go-gh/v2 (GitHub API/auth), cobra (CLI), cenkalti/backoff/v5 (retry). Auth is inherited from gh automatically.

Read the full file on GitHub · 47 lines

Changes

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.

  1. 8d ago First seen · 47 lines · 688 tokens per session scan A 6f8559bed5fe

Subscribe to this mod's changes

gh-watch CLAUDE.md is an instructions file published in the GitHub repository justincampbell/gh-watch (4 stars, last pushed 20d ago), licensed MIT. It adds 688 tokens to every session, about $0.0034 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.

Claude CodeGit and workflowciclaude-code-plugincligh-extensiongithub-actions
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens