codecast: Instructions file for Codex

AGENTS.md

codecast AGENTS.md is an instructions file for Codex, OpenCode from codecast-sh/codecast. It costs 4,619 tokens per session, scanned A, original, MIT.

A set of repository instructions for working on the Codecast codebase. It explains where to work, how to handle generated copies of shared packages, and how to check Git changes and deployment-related files.

In plain words
What is it for?
Use it when modifying Codecast, especially when changing shared platform packages, refreshing their vendored mirror, checking repository state, or preparing Convex and release deployments.
Why use it?
It prevents edits to generated files, accidental loss of other people's uncommitted work, and stale local package or build caches. It also documents how shared platform code is kept consistent with the checkout.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is codecast-sh/codecast's own configuration. It tells Codex and OpenCode how to work on codecast itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codecast configures →

Reuse

Borrowing it

Nothing to install: this file belongs to codecast-sh/codecast. 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/codecast-sh/codecast/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/codecast-sh/codecast

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.

agentmods badge for codecast AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/codecast-sh/codecast/agents-md/github.svg)](https://agentmods.dev/instructions/codecast-sh/codecast/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/codecast-sh/codecast/agents-md"><img src="https://agentmods.dev/badge/instructions/codecast-sh/codecast/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.

agentmods 80×15 button for codecast AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/codecast-sh/codecast/agents-md"><img src="https://agentmods.dev/badge/instructions/codecast-sh/codecast/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,619 This file is loaded in full into every session.
When invoked 4,619 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04619 $0.04619
Opus 5 $0.02309 $0.02309
Sonnet 5 $0.00924 $0.00924
Haiku 4.5 $0.00462 $0.00462

Measured today against content hash 998e480552a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

codecast 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 today.

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 · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codecast

Working directory

Work directly in the main checkout. Other sessions may have uncommitted work in the tree — scan git status/git diff before editing shared files and never revert changes you didn't make.

Vendored platform packages

platform/packages/ is a GENERATED mirror of the shared @platform/* packages whose canonical home is ~/src/platform. Never edit it by hand: change the canonical copy, then run scripts/vendor-platform.sh to refresh the mirror (--check reports drift). The script also purges bun's node_modules/.bun/@platform+* copies and packages/web/node_modules/.vite and reinstalls, because bun keeps serving the stale copy and vite the stale module graph otherwise. A running dev server restarts itself when that cache disappears (plugins/depsCacheGuard.ts); never delete the cache under a live server without that plugin, or every dep it has not served yet answers 504 "Outdated Optimize Dep". The mirror exists because Railway, the CLI release workflow and the desktop build all run from a fresh clone, so every @platform dep must point inside the checkout (file:../../platform/packages/<name>), never at ~/src/platform. The package set is derived from the workspace package.json files, so adopting a new platform package is one dep line plus a rerun. A real vendor run also rewrites platform/vendor-manifest.txt, a content hash per mirrored package; commit it with the mirror. CI cannot run --check, because a runner has no ~/src/platform, so the test-platform job runs --check-manifest instead: it re-hashes the mirror against that manifest and re-reads the dep lines the mirror was generated from, which catches a hand-edited mirror, a package adopted without a rerun, and a dep pointing outside the checkout. The same job runs each mirrored package's own bun test, installing inside the package first because the mirror is not a workspace member and its deps resolve nowhere from the repo root.

Git history

Keep history flat — rebase, never merge. Pull with git pull --rebase (never plain git pull when it would create a merge commit), and bring branches up to date with git rebase origin/main instead of merging main in. Merge commits from routine syncing don't belong in the log.

Read the full file on GitHub · 161 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. today Changed · +142 tokens per session 998e480552a8
  2. yesterday First seen · 161 lines · 4,477 tokens per session scan A 57a4065644ee

Subscribe to this mod's changes

codecast AGENTS.md is an instructions file published in the GitHub repository codecast-sh/codecast (30 stars, last pushed today), licensed MIT. It adds 4,619 tokens to every session, about $0.0231 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 2026-09-07.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 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 · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens