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/hoatv2211/gamestudio-codexkit/agents-mdgit clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKITWrote 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/hoatv2211/gamestudio-codexkit/agents-md)<a href="https://agentmods.dev/instructions/hoatv2211/gamestudio-codexkit/agents-md"><img src="https://agentmods.dev/badge/instructions/hoatv2211/gamestudio-codexkit/agents-md.svg" alt="Measured on agentmods" 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 | $0.01547 | $0.01547 |
| Opus 5 | $0.00773 | $0.00773 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
GameStudio-CodexKIT 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GameStudio-CodexKIT Operating Contract
Active Sources Of Truth
Use this precedence order:
AGENTS.mdfor operating, evidence, mutation, ownership, archive, and handoff rules..agents/skills/*/SKILL.mdand.codex/agents/*.tomlfor repository-local maintenance behavior while working in this repository.registry/*.yamlfor distributed capabilities, agent roles, packs, personas, skill resources, and upstream snapshot provenance.skills/*/SKILL.mdfor canonical distributed workflows.docs/architecture/overview.mdanddocs/authoring/skills.mdfor maintained design guidance.- Generated adapters as read-only optional export artifacts.
Files under the ignored local .archive/ are optional historical context only and never active policy or distributable template content.
Primary Distribution
- Codex App/CLI and Hermes Agent are the only primary runtime targets. Treat every other export as optional maintenance output.
- The repository root is the installable plugin;
skills/remains the only canonical distributed workflow source. .codex-plugin/plugin.jsondefines the plugin identity and exposes./skills/directly..claude-plugin/marketplace.jsonis the Codex-supported repository marketplace compatibility path used by the GitHub install flow.- Hermes Agent installs the same canonical catalog through
npx skills add <repo> -a hermes-agent; the CLI copies individual skill directories, so runtime helpers must be bundled inside each skill. - Generated Hermes, Codex, pack, and per-project outputs are optional export artifacts. Canonical agent-role templates live in
agents/and are materialized project-locally; never create a second hand-maintained plugin skill tree. - Keep Codex plugin metadata, the Hermes Agent-discoverable root catalog, repository URL, and registry synchronized through
scripts/validate.pyand packaging tests. - Increment the plugin semantic version when a distributed plugin change must invalidate an installed cache.
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.
- 4d ago First seen · 104 lines · 1,547 tokens per session scan A 5d022e16605f
GameStudio-CodexKIT AGENTS.md is an instructions file published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 1,547 tokens to every session, about $0.0077 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
do-it AGENTS.md
AGENTS.md instructions for tdwhere123/do-it, covering agents.md, file rules, repository, source of truth vs build artifacts and closed-set contracts.
odin-codex-plugin AGENTS.md
AGENTS.md instructions for OutlineDriven/odin-codex-plugin, covering codex coding agent adherences, token-efficient cli output, tool hierarchy, core system & file ops and search & discovery.
m2ui-skill copilot-instructions.md
Copilot instructions for martysama0134/m2ui-skill, covering m2ui — metin2 ui code generator, mode detection, reference documentation, two ui styles and critical code generation rules.
simple-man CLAUDE.md
Instructions for Maksim-Burtsev/simple-man, a project described as: Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.
pinotator AGENTS.md
AGENTS.md instructions for transcendr/pinotator, covering goal queue prompt routing, goal queue processing and semantics and git tracking rules.
init-claude-md CLAUDE.md
Claude Code instructions for LetheChen/init-claude-md, covering agents.md, session maintenance protocol, core rules (from karpathy), language and project conventions.