Borrowing it
Nothing to install: this file belongs to guruswami-ai/not-happy-jan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/guruswami-ai/not-happy-jan/main/AGENTS.mdgit clone --depth 1 https://github.com/guruswami-ai/not-happy-janWrote 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/guruswami-ai/not-happy-jan/agents-md)<a href="https://agentmods.dev/instructions/guruswami-ai/not-happy-jan/agents-md"><img src="https://agentmods.dev/badge/instructions/guruswami-ai/not-happy-jan/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/guruswami-ai/not-happy-jan/agents-md"><img src="https://agentmods.dev/badge/instructions/guruswami-ai/not-happy-jan/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01660 | $0.01660 |
| Opus 5.5 | $0.00664 | $0.00664 |
| Sonnet 5.5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
not-happy-jan 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 5d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo with more than one agent
Several coding agents (and a human) can work on Not-Happy-Jan at the same time, and a running NHJ install executes code from a checkout of this repo. These rules keep them from clobbering each other and from changing a live install by accident. They apply to every agent (Claude Code, Codex, opencode, Muse, ...) and to people.
One working directory per agent
A directory has exactly one checked-out branch, so two agents in one directory fight over it
(one git checkout and the other's next commit lands on the wrong branch). Use git worktrees:
same repository, separate directories.
git fetch origin
git worktree add ../nhj-<agent> -b <agent>/<topic> origin/main # your own, e.g. ../nhj-claude
git worktree add --detach ../nhj-live origin/main # the live checkout, once
- Edit and commit only in your own worktree. Never
git checkout,git resetor edit files in someone else's. - Name branches
<agent>/<topic>(claude/…,codex/…,muse/…). Keep them short-lived. mainis protected: change it only through a pull request with the required checks green. Never push tomain; never force-push a branch somebody else is using.- Stage and commit explicit paths. A directory has one git index, so anything another agent
has staged there is committed by your
git commit. That is how an unreviewed file ended up in a merged PR. In your own worktree:git add <paths>(notgit add -A/git commit -a), readgit diff --cached --statbefore every commit, and prefergit commit <paths>. - Give each worktree its own virtual environment (
uv venv && uv pip install -e ".[server,dev]"): an editable install is tied to the directory it was made from.
The live checkout is read-only
Hooks, the nhj command and any service unit should point at a detached worktree of origin/main
that nobody edits. Updating it is a deliberate step after a merge:
scripts/update-live.sh /path/to/nhj-live # fast-forwards to origin/main, reinstalls, restarts services
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.
- 5d ago First seen · 110 lines · 1,660 tokens per session scan A f8770a1e995f
not-happy-jan AGENTS.md is an instructions file published in the GitHub repository guruswami-ai/not-happy-jan (0 stars, last pushed 2d ago), licensed MIT. It adds 1,660 tokens to every session, about $0.0066 per session on Opus 5.5. 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 2026-10-25.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.