Borrowing it
Nothing to install: this file belongs to educates/educates-training-platform. 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/educates/educates-training-platform/develop/AGENTS.mdgit clone --depth 1 https://github.com/educates/educates-training-platformWrote 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/educates/educates-training-platform/agents-md)<a href="https://agentmods.dev/instructions/educates/educates-training-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/educates/educates-training-platform/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/educates/educates-training-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/educates/educates-training-platform/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 | $0.05912 | $0.05912 |
| Opus 5.5 | $0.02365 | $0.02365 |
| Sonnet 5.5 | $0.01182 | $0.01182 |
| Haiku 4.5 | $0.00591 | $0.00591 |
Grade A, and why
educates-training-platform 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 yesterday.
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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Briefing for AI agents working in this repository. Read it fully before doing anything substantial. Sections are ordered by importance — the top is what changes day-to-day, the bottom is mostly stable.
The install path
The install pipeline is a Helm chart + Go operator. There is one install path; the old v3 Carvel-based installer (kapp-controller) is gone.
- CLI flow:
educates admin platform deploy(helm install the operator chart +kubectl applythe 4 platform CRs), oreducates local cluster createfor the laptop flow (kind + registry + deploy in one). - No in-place v3 migration. Users on v3 delete their old install and
follow the v4 path. The CLI silently migrates a v3
values.yaml→ v4config.yamlon first run when the v3 provider was kind (or empty); other providers get a clear re-declare error. - CLI config is a kind ladder (
cli.educates.dev/v1alpha1):EducatesLocalConfig(laptop; lives at<data-home>/config.yaml), scenario kindsEducatesGKEConfig/EducatesEKSConfig/EducatesInlineConfig, and theEducatesConfigescape hatch (CR specs verbatim, no CLI defaults). JSON schemas are embedded atclient-programs/pkg/config/v1alpha1/schemas/. Data home is$XDG_DATA_HOME/educates/, overridable viaEDUCATES_CLI_DATA_HOME.
ytt is the only Carvel library in the CLI. It templates workshop
definitions for the workshop commands (the --data-value* flags). The
CLI builds and pushes workshop and extension package images itself, with
go-containerregistry. Sessions still download content with the vendir
and imgpkg binaries in the base image (workshop-images/).
The Educates runtime is Python/kopf/Django. Components in
session-manager/, secrets-manager/, lookup-service/,
training-portal/, tunnel-manager/, workshop-images/, and supporting
services keep those implementations. The installer is the operator + chart;
it installs the runtime but does not reimplement it.
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.
- yesterday Changed · +2 lines · +35 tokens per session 03cb66d727e2
- 7d ago Changed · +5 lines · +89 tokens per session 63d871ae8dff
- 8d ago Changed · +9 lines · +157 tokens per session 737b93014b9c
- 10d ago Changed · +14 lines · +194 tokens per session 8c166955be46
- 12d ago Changed · -1 tokens per session b029a8aeca1b
- 21d ago First seen · 461 lines · 5,438 tokens per session scan A 33a5d4057eed
educates-training-platform AGENTS.md is an instructions file published in the GitHub repository educates/educates-training-platform (163 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,912 tokens to every session, about $0.0236 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 2026-10-16.
educates-training-platform AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| educates-training-platform AGENTS.mdeducates/educates-training-platform | Instructions file | 163 | 2d ago | Apache-2.0 | A | 5,912 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |