Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/dojo-coder/sensei/agents-mdgit clone --depth 1 https://github.com/dojo-coder/senseiWhat 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 | $0.35969 | $0.35969 |
| Opus 5 | $0.17985 | $0.17985 |
| Sonnet 5 | $0.07194 | $0.07194 |
| Haiku 4.5 | $0.03597 | $0.03597 |
Grade A, and why
sensei 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 2d 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 — 2,513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DojoCode Resource Curator - Agent Guidelines
This file provides comprehensive context for AI curators on how to create, structure, and manage all DojoCode resource types by calling the dojocode MCP tools: coding challenges, contests, learning paths, projects, and assignments.
The document is organized in parts. Read the Session start section first (it applies to every workflow), then jump to the part for the resource you are creating:
- Part 1 — Challenges: full file-based authoring (starter code, solutions, tests), packaging, upload, and test execution. This is the largest part and the foundation the other resources build on. Starts at "Challenge Creation Process" below.
- Part 2 — Contests: assemble existing challenges into a timed competition (
create_contest). - Part 3 — Learning Paths: assemble existing challenges into a guided, lesson-by-lesson path (
create_learning_path). - Part 4 — Projects: create a free-form sandbox project from a template and a file tree (
create_project). - Part 5 — Assignments: assign a learning path or a challenge to students / groups (
create_assignment).
Organizations / workspace. Business work (contests, assignments, student groups, and the content that belongs to them) is scoped to an organization workspace. Establish the active workspace at session start with
get_my_organizations→select_organizationbefore any org-scoped operation — see Organization workspace under Session start.
Each resource type has its own top-level folder in this repo (challenges/, contests/, learning-paths/, projects/, assignments/) with a committed *-example descriptor inside it, while the full library of challenge template samples lives under challenges/challenge-samples/. Contests, learning paths, and assignments reference existing challenges (and learning paths) by their platform _id — always resolve those IDs first via get_my_challenges / get_challenges / get_my_learning_paths before calling a create tool. Parts 2–5 and their MCP workflows live at the end of this file, after the challenge workflows.
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.
- 2d ago First seen · 2,513 lines · 35,969 tokens per session scan A 4c839d27251a
sensei AGENTS.md is an instructions file published in the GitHub repository dojo-coder/sensei (2 stars, last pushed 1mo ago), licensed MIT. It adds 35,969 tokens to every session, about $0.1798 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.