agentmods.dev

truecourse AGENTS.md

A set of coding instructions for the TrueCourse project, including its important files, folder layout, development commands, and project rules. TrueCourse contains a dashboard, server, shared code, and code-analysis packages.

In plain words
What is it for?
Use it when changing TrueCourse features, packages, endpoints, commands, environment variables, or project structure, and when updating `PLAN.md` or `README.md`.
Why use it?
It keeps project plans, documentation, structure, and implementation status aligned as the codebase changes.

Instructions file for CodexOpenCode

523 5d ago A scan 689 tokens original MIT
View the source file truecourse-ai/truecourse
Install

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.

agentmods
npx agentmods add instructions/truecourse-ai/truecourse/agents-md
Clone the repo
git clone --depth 1 https://github.com/truecourse-ai/truecourse

Made for: Codex, OpenCode.

Per session 689 This file is loaded in full into every session.
When invoked 689 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00689 $0.00689
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash e126b1df2da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

truecourse 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 3d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TrueCourse — Codex Instructions

Key Files to Keep Updated

  • PLAN.md — The source of truth for all phases, implementation status, and test plans. When completing work on any phase or sub-task, update the relevant STATUS: tags. When adding new features or changing scope, update the plan accordingly.
  • README.md — Must reflect the current state of the project. When adding new packages, endpoints, commands, environment variables, or changing the project structure, update the README to match.

Project Layout

  • apps/dashboard/client/ — Vite + React Router frontend (React Flow graph, Tailwind CSS, dark mode)
  • apps/dashboard/server/ — Express + Socket.io HTTP layer that serves the dashboard. Thin adapter over @truecourse/core.
  • packages/core/ — Framework-agnostic analysis engine: pipeline, graph/flow services, LLM providers, persistence, config, logger. Consumed by both the CLI and the dashboard server.
  • packages/shared/ — Shared Zod schemas and TypeScript types
  • packages/analyzer/ — Tree-sitter + TypeScript Compiler analysis engine (TS/JS/Python)
  • tools/cli/ — CLI commands (analyze, dashboard, list, add, rules). Thin adapter over @truecourse/core — does NOT depend on the dashboard server.
  • tests/ — All tests (centralized, not colocated). Organized by package: tests/shared/, tests/analyzer/, tests/server/ (covers both dashboard-server routes and core services), tests/cli/.
  • tests/fixtures/sample-project/ — Realistic multi-service TS/JS repo used by tests

Development Commands

pnpm dev          # Start all services (turbo) — file-based store under <repo>/.truecourse/
pnpm build        # Build all packages
pnpm build:dist   # Build distributable npm package (static frontend + bundled server → dist/)
pnpm test         # Run all tests (vitest)

Rules

  • No workarounds. Always find and fix the root cause. Do not use hacks, fallbacks, or temporary patches to bypass issues. If something isn't working, investigate why and fix it properly.
  • Dev servers. Do not start, stop, or restart dev servers. The user manages pnpm dev from their terminal. If a restart is needed (e.g. .env change), tell the user.
  • Storage. The store is file-based (no DB). Writes go through packages/core/src/lib/analysis-store.ts via atomicWriteJson. Reads are mtime-cached on LATEST.json. Concurrent analyses are prevented by .analyze.lock (O_EXCL).

Read the full file on GitHub · 41 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.

  1. 3d ago First seen · 41 lines · 689 tokens per session scan A e126b1df2da0

Subscribe to this mod's changes

truecourse AGENTS.md is an instructions file published in the GitHub repository truecourse-ai/truecourse (523 stars, last pushed 5d ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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.

aiarchitecturecode-analysiscode-qualitydeveloper-toolslinter
Related

Other instructions, from other repositories

static-analysis AGENTS.md

Instructions for analysis-tools-dev/static-analysis, covering guidelines for ai agents and assistants and 🤖 instructions for the ai.

analysis-tools-dev/static-analysis · 332 tokens

fallow CLAUDE.md

Claude Code instructions for fallow-rs/fallow, covering fallow repository adapter for claude, knowledge layers, workflow, trust boundary and generated surfaces.

fallow-rs/fallow · 370 tokens

roam-code AGENTS.md

Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).

Cranot/roam-code · 14,242 tokens

PhpCodeArcheology CLAUDE.md

Instructions for PhpCodeArcheology/PhpCodeArcheology, covering claude.md — phpcodearcheology, project overview, language, tech stack and project structure.

PhpCodeArcheology/PhpCodeArcheology · 976 tokens

megalinter CLAUDE.md

Claude Code instructions for oxsecurity/megalinter, covering claude.md, project overview, development setup, shell commands — use rtk and key commands.

oxsecurity/megalinter · 2,792 tokens

prodlint CLAUDE.md

Instructions for prodlint/prodlint, covering claude.md, commands, architecture, scan flow and rule interface.

prodlint/prodlint · 2,686 tokens