Borrowing it
Nothing to install: this file belongs to opensupplyhub/open-supply-hub. 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/opensupplyhub/open-supply-hub/main/AGENTS.mdgit clone --depth 1 https://github.com/opensupplyhub/open-supply-hubWrote 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/opensupplyhub/open-supply-hub/agents-md)<a href="https://agentmods.dev/instructions/opensupplyhub/open-supply-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/opensupplyhub/open-supply-hub/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/opensupplyhub/open-supply-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/opensupplyhub/open-supply-hub/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 | $0.01399 | $0.01399 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
open-supply-hub 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Quick Start Guide
Repository Structure
Those are the main directories in the project, other ones are not relevant for the agents:
doc- all the documentation for the project, including the architecturescripts- helper scripts to run specific tasks and commandsdeployment- infra configuration and deployment scriptssrc- source code for the for different services and parts of the systemanon-tools- anonymization tools used to anonymize the database for testing and development purposesdjango- Django backend, this our main API Gateway and backend for the systemdedupe-hub- dedupe hub, this is a tool that helps us deduplicate the data, connects with the Django backend and Kafka for matching and deduplicatione2e- end to end tests for the system, currently NOT being developed in this repologstash- logstash, this is a tool that helps us index the data into OpenSearchreact- React frontend, this is the main frontend for the system
Running the system
IMPORTANT: Use docker compose to run the system, don't run the commands directly.
- To run the system in development mode, you can use the following command:
docker compose up -d
Testing
- Use docker compose to run the tests. For example, to run the UI tests you can use the following command:
docker compose exec react yarn test --watchAll=false
- To run the tests for the Django backend, you can use the following command:
docker compose exec django python manage.py test
Data moderation
- To get a first pass at tagging a ContriBot ~PROCESSED sheet, use the list-review skill. It proposes taxonomy tags against the team's moderation bar and produces the tagged rows, the summary and the draft email in one go. Every tag is a suggestion the moderator reviews and can overrule; it never sends email and never changes list state.
- Accepts a local CSV path, a Google Drive link or file id, or a bare list id.
- Writes to
<output_dir>/<list id>/:tagged.csv+tagged.html(tagged rows only),summary.md+summary.html(counts, error ratio, scenario recommendation, checklist),email.md+email.html(draft contributor email).
- To generate a contributor feedback email from tags a moderator has already applied themselves, use the moderation-email skill. It never adds or changes tags and never sends email.
- Accepts a Google Sheets link to the tagged tab of a ~PROCESSED report, or a local CSV export of that tab.
- Writes to
<output_dir>/<list id>/:tagged.csv(parsed tags),email.md+email.html.
- Both require the Google Drive integration and the same per-moderator config file at
~/.config/os-hub/moderation-email.json— copy.agent/skills/_shared/config.example.jsonand fill it from the internal Data Team Resources page. Every document id, board URL, policy threshold andoutput_dircomes from that file; neither skill has defaults, and both stop rather than guess if it is missing.
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 Changed · +10 lines · +393 tokens per session ed7eca90cb55
- 8d ago First seen · 84 lines · 1,006 tokens per session scan A d17e8ea55e8e
open-supply-hub AGENTS.md is an instructions file published in the GitHub repository opensupplyhub/open-supply-hub (20 stars, last pushed yesterday), licensed MIT. It adds 1,399 tokens to every session, about $0.0070 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 2026-08-30.
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.
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.
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).
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).
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.
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.