Borrowing it
Nothing to install: this file belongs to DIGI-UW/OpenELIS-Global-2. 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/DIGI-UW/OpenELIS-Global-2/develop/AGENTS.mdgit clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2Wrote 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/digi-uw/openelis-global-2/agents-md)<a href="https://agentmods.dev/instructions/digi-uw/openelis-global-2/agents-md"><img src="https://agentmods.dev/badge/instructions/digi-uw/openelis-global-2/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/digi-uw/openelis-global-2/agents-md"><img src="https://agentmods.dev/badge/instructions/digi-uw/openelis-global-2/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 | $0.21663 | $0.21663 |
| Opus 5.5 | $0.08665 | $0.08665 |
| Sonnet 5.5 | $0.04333 | $0.04333 |
| Haiku 4.5 | $0.02166 | $0.02166 |
Grade A, and why
OpenELIS-Global-2 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 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.
How it starts
The opening of the file, as written. The whole thing — 2,507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - README for AI Coding Agents
Start here — do these three things before any other work
These are not optional and not "if needed". Skipping them is the single most common way an agent wastes a session in this repository.
1. Install the agent command assets
python3 scripts/install-agent-skills.py -y claude
This installs /fix-ci, /download-ci-logs, /address-pr-comments,
/careful-rebase and ~22 others, plus the packaged skills.
.claude/ is gitignored. It is created by this script, not by git clone
and not by git pull. A second clone or worktree of this repository therefore
has no commands at all until you run the installer there — and nothing warns
you, the commands are simply absent. Run it once per checkout, including every
worktree.
2. Never judge CI from a run's conclusion
Use gh pr checks <PR>. It matches the GitHub UI and exits non-zero unless
everything passes.
gh pr checks 1234 # the whole picture
gh pr checks 1234 | grep -E "fail" # just the failures
The three build checkpoints are 01 Checkpoint - Backend,
02 Checkpoint - Frontend, and 03 Checkpoint - E2E. The trusted
Validation / Submodule pins check is also required after its rollout below.
Early in a run only some checks exist, so confirm all required checks are
present and none are pending before calling a PR green.
Do not use gh run watch --exit-status: 03 Checkpoint - E2E is posted by
a workflow_run follow-up stage, so the underlying run's own conclusion does
not tell you whether the checkpoint passed, and gh run watch exits 0 on
failure for this pipeline. Do not write ad hoc jq over statusCheckRollup
either: it mixes CheckRun nodes (.conclusion) with StatusContext nodes
(.state), an in-flight check reports an empty conclusion rather than null, and
a re-run leaves the earlier run of a check in the list. Naive jq reports
passing checks as queued and single checks as "all green";
scripts/download-ci-logs.sh handles all three.
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.
- 8d ago Changed · +3 lines · +53 tokens per session f006ad98180e
- 9d ago Changed · +2 lines · +30 tokens per session 4a6833d3d0bb
- 11d ago Changed · -59 lines · -691 tokens per session d94a04ee9139
- 15d ago Changed · +26 lines · +379 tokens per session 9223faf5e8c0
- 17d ago Changed · -36 lines · -4 tokens per session 236dac224b8c
- 19d ago Changed · +17 lines · +257 tokens per session 8faad2150674
- 20d ago Changed 07f8d19c46be
- 21d ago Changed · -1 tokens per session 2396c2ff07c5
- 22d ago Changed · +42 tokens per session 876da49f3098
- 25d ago First seen · 2,554 lines · 21,598 tokens per session scan A 6278e983f3c8
OpenELIS-Global-2 AGENTS.md is an instructions file published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (272 stars, last pushed today), licensed MPL-2.0. It adds 21,663 tokens to every session, about $0.0867 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 2026-08-30.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).