What is shadow-tutor AGENTS.md?

Repository instructions for coding agents working on Shadow Tutor, a tool that teaches developers during and after coding sessions. They describe the project layout, rules, and ways to build, test, and evaluate changes.

Use them when changing Shadow Tutor, running its tests or evaluations, or regenerating its plugin files.

They give an agent the project-specific context needed to make small, checked changes without breaking synchronized copies of the skill.

How lzfxxx/shadow-tutor configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to lzfxxx/shadow-tutor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lzfxxx/shadow-tutor/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/lzfxxx/shadow-tutor

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lzfxxx/shadow-tutor/agents-md/github.svg)](https://agentmods.dev/instructions/lzfxxx/shadow-tutor/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lzfxxx/shadow-tutor/agents-md"><img src="https://agentmods.dev/badge/instructions/lzfxxx/shadow-tutor/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lzfxxx/shadow-tutor/agents-md"><img src="https://agentmods.dev/badge/instructions/lzfxxx/shadow-tutor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 796 This file is loaded in full into every session.

When invoked 796 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00796	$0.00796
Opus 5.5	$0.00318	$0.00318
Sonnet 5.5	$0.00159	$0.00159
Haiku 4.5	$0.00080	$0.00080

Measured 2mo ago against content hash baf006a05843, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shadow-tutor 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 2mo 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — repository instructions for coding agents

Shadow Tutor is an in-session post-session tutor delivered as a native skill for both Codex and Claude Code. The product is skills/shadow-tutor/METHODOLOGY.md (a teaching methodology) plus thin supporting code. Keep changes small, evidence-checked, and language-neutral.

Layout in one line

skills/shadow-tutor/ is the product — a self-contained skill bundle (SKILL.md + METHODOLOGY.md + scripts/knowledge.mjs) that every install path (npx skills add, plugin marketplace, install.sh, npx shadow-tutor install) copies verbatim. Never fork per-tool copies; plugins/ is generated from it by node bin/cli.mjs build.

Build / test / eval

npm test            # node:test unit tests — must stay green
npm run eval:dry    # assemble eval prompts without model calls (no quota needed; CI-safe)
npm run eval        # real eval via `claude -p` / `codex exec` — simulated-student dialogue + rubric
node bin/cli.mjs build   # regenerate plugins/shadow-tutor/ after changing the bundle (CI checks sync)
./install.sh        # install the skill into ~/.claude/skills and ~/.codex/skills

There is no build step for the skill itself; everything is plain ESM .mjs and markdown.

Mandatory rules (if/then)

Before editing skills/shadow-tutor/ (especially METHODOLOGY.md), follow docs/dev/eval-regression.md: run the eval and confirm the rubric score does not drop (must stay ≥13, no regression on existing fixtures). Teaching quality is the product; a silent regression here is the worst failure mode.
When adding a recorded coding session as a test fixture, follow docs/dev/add-fixture.md to normalize it and place it under eval/fixtures/{cc,codex}/.
When changing skills/shadow-tutor/scripts/knowledge.mjs, add or update a case in scripts/knowledge.test.mjs and keep npm test green.
After changing anything under skills/shadow-tutor/ or claude/commands/, run node bin/cli.mjs build and commit the regenerated plugins/.

Read the full file on GitHub · 58 lines

Changes

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.

2mo ago First seen · 58 lines · 796 tokens per session scan A baf006a05843

Subscribe to this mod's changes

shadow-tutor AGENTS.md is an instructions file published in the GitHub repository lzfxxx/shadow-tutor (4 stars, last pushed 4mo ago), licensed MIT. It adds 796 tokens to every session, about $0.0032 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.

Claude Code Learning and teaching agent-skills agents-md ai-coding codex developer-education

ai-agent-rules-generator agent-observations.instructions.md

Mandatory agent observation logging — anomalies, recommendations, and critical findings must be disclosed before commit.

savedpixel/ai-agent-rules-generator · 1,787 tokens

ai-agent-rules-generator doc-sync.instructions.md

Documentation sync rules — which docs to update when code changes.

savedpixel/ai-agent-rules-generator · 1,652 tokens

ai-agent-rules-generator ratelimitting.instructions.md

Instructions for savedpixel/ai-agent-rules-generator, covering rate limit prevention (critical), rules, output length limits and visibility.

savedpixel/ai-agent-rules-generator · 522 tokens

ai-agent-rules-generator ui-design.instructions.md

Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.

savedpixel/ai-agent-rules-generator · 701 tokens

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

shadow-tutor: Instructions file for Codex