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/dubsopenhub/groundhog-day/agents-mdgit clone --depth 1 https://github.com/DUBSOpenHub/groundhog-dayWrote 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.
[](https://agentmods.dev/instructions/dubsopenhub/groundhog-day/agents-md)<a href="https://agentmods.dev/instructions/dubsopenhub/groundhog-day/agents-md"><img src="https://agentmods.dev/badge/instructions/dubsopenhub/groundhog-day/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00900 | $0.00900 |
| Opus 5 | $0.00450 | $0.00450 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
groundhog-day AGENTS.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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: Working Guide for AI Agents
This file tells any AI agent how to work effectively on the Groundhog Day codebase.
Architecture
Groundhog Day is a standalone bash daemon that watches ~/.copilot/skills/ and auto-syncs changes to a GitHub repository. It is NOT a Copilot CLI skill — it's infrastructure that protects skills.
~/bin/groundhog ← main script (bash)
├── watch mode (fswatch → rsync → git) ← real-time file watcher
├── sync (rsync + git add/commit/push) ← core sync logic
├── checkup (13-point diagnostic) ← daily health check at 6 AM
└── status (quick health check) ← manual status
~/Library/LaunchAgents/
├── com.dubsopenhub.groundhog.plist ← keeps watcher alive
└── com.dubsopenhub.groundhog.checkup.plist ← nightly checkup at 6 AM
File Ownership Map
| File | Purpose | Change Rules |
|---|---|---|
groundhog |
Main script | All logic lives here. Test with groundhog checkup after changes. |
install.sh |
One-line installer | Must stay idempotent. Re-running should not break existing installs. |
com.dubsopenhub.groundhog.plist |
LaunchAgent (watcher) | KeepAlive=true. Update home dir paths if changing user support. |
com.dubsopenhub.groundhog.checkup.plist |
LaunchAgent (nightly) | Runs at 6 AM. No KeepAlive — runs once and exits. |
README.md |
Documentation | Keep GIFs, keep the tone. Don't remove the Bill Murray energy. |
Key Design Decisions
1. No external dependencies beyond standard tools
Groundhog Day uses only: bash, fswatch, rsync, git, python3 (stdlib only). No pip packages. No node modules. This is intentional — it must survive on a fresh machine with just Homebrew basics.
2. Single file architecture
Everything lives in one bash script. No splitting into modules. This keeps installation trivial (cp one file) and debugging simple (cat one file).
3. Lock file for concurrency
/tmp/groundhog.lock is a directory-based lock (atomic on all filesystems). mkdir succeeds or fails atomically. Always release with trap ... RETURN.
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.
- 4d ago First seen · 81 lines · 900 tokens per session scan A ce63c8cfd364
groundhog-day AGENTS.md is an instructions file published in the GitHub repository DUBSOpenHub/groundhog-day (5 stars, last pushed 2mo ago), licensed MIT. It adds 900 tokens to every session, about $0.0045 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
Build-CLI AGENTS.md
Instructions for microsoft/Build-CLI, covering agents.md, plugin ecosystems, sync rules, cli and cli behavior contracts.
spec-kit-copilot AGENTS.md
Instructions for github/spec-kit-copilot, covering what this repository is, core skills plugin, core decisions (do not silently undo) and when revving the core skills plugin.
sts2-llm copilot-instructions.md
Instructions for ttxttx1111/sts2-llm, covering copilot instructions for this repository, source of truth for customizations, runtime assumptions, authoring rules for this repo and gameplay-specific expectations.
sts2-llm skills.instructions.md
Instructions for ttxttx1111/sts2-llm, covering skill 文件与变更记录说明, 基本规则, 修改 skill 时的最小要求, 何时要同步更新总文档 and 工作方式.
sts2-llm runtime.instructions.md
Instructions for ttxttx1111/sts2-llm, a project described as: GitHub Copilot player agent customization pack for Slay the Spire 2 via STS2MCP.
sts2-llm live-data.instructions.md
Instructions for ttxttx1111/sts2-llm, a project described as: GitHub Copilot player agent customization pack for Slay the Spire 2 via STS2MCP.