Borrowing it
Nothing to install: this file belongs to joeszilagyi/Upkeeper. 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/joeszilagyi/Upkeeper/main/AGENTS.mdgit clone --depth 1 https://github.com/joeszilagyi/UpkeeperWrote 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/joeszilagyi/upkeeper/agents-md)<a href="https://agentmods.dev/instructions/joeszilagyi/upkeeper/agents-md"><img src="https://agentmods.dev/badge/instructions/joeszilagyi/upkeeper/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/joeszilagyi/upkeeper/agents-md"><img src="https://agentmods.dev/badge/instructions/joeszilagyi/upkeeper/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 | $0.03280 | $0.03280 |
| Opus 5.5 | $0.01312 | $0.01312 |
| Sonnet 5.5 | $0.00656 | $0.00656 |
| Haiku 4.5 | $0.00328 | $0.00328 |
Grade A, and why
Upkeeper 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 14d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Contract
This repository is the central source of truth for Upkeeper wrapper behavior.
Repository Layout
Upkeeperis the executable entrypoint and loader for the central wrapper.lib/upkeeper/*.bashcontains sourced runtime modules. Keep module changes narrow and respect the load-order notes inlib/upkeeper/README.md.prompts/*.mdcontains default and opt-in review-module contracts.docs/contains public operator documentation.docs/scripts/upkeeper.mdmirrors operator-facing help and must stay aligned with./Upkeeper --help.tools/contains deterministic local validation and corpus harnesses.tests/*.bashcontains focused local unit tests.testruns/*.shcontains operator launchers for repeatable dry-run/live scenarios.runtime/,Upkeeper.log, transcripts, manifests, locks, and postmortem artifacts are local evidence and must not be committed.
Planning Rules
- For complex changes, create or update root
PLANS.mdbefore broad editing. A complex change is one that spans multiple runtime modules, changes a public contract, changes target selection, changes config semantics, alters fallback or quota behavior, or needs more than one meaningful implementation step. - Keep
PLANS.mdpractical: goal, constraints, files likely touched, validation commands, rollout/compatibility notes, and current status are enough. - Small single-file docs or test-only patches do not need a plan unless the user asks for one.
- Do not run real backend Codex validation unless the user explicitly requests
it. Prefer
UPKEEPER_DRY_RUN=1, fake Codex fixtures, unit tests, and the local stress corpus.
Required Validation Commands
Use the smallest command set that covers the change, and record anything that could not be run.
For shell/runtime changes in Upkeeper, lib/upkeeper, tools, tests,
testruns, config files, or launcher examples:
bash tools/check_shell_syntax.sh
tools/run_tests.sh
git diff --check
tools/validate_upkeeper.sh --quick
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.
- 14d ago Changed · +16 lines · +202 tokens per session 7432ccbc4dbf
- 19d ago Changed · +23 lines · +300 tokens per session 0112b5353ee1
- 2mo ago First seen · 265 lines · 2,778 tokens per session scan A 5306a9dd6c21
Upkeeper AGENTS.md is an instructions file published in the GitHub repository joeszilagyi/Upkeeper (2 stars, last pushed 14d ago), licensed MIT. It adds 3,280 tokens to every session, about $0.0131 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 2026-08-31.
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).
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.