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 skills add nxtg-ai/forge-plugin --skill codex-frameworkgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/skills/nxtg-ai/forge-plugin/codex-framework)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/codex-framework"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/codex-framework/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.
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/codex-framework"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/codex-framework.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00118 | $0.01754 |
| Opus 5.5 | $0.00047 | $0.00702 |
| Sonnet 5.5 | $0.00024 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
Codex Framework scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex CLI — Reference Knowledge
REFERENCE ONLY. Do NOT create
AGENTS.md,AGENTS.override.md,SKILLS.md, or.agents/on your own initiative. NXTG-Forge delivers agents and skills through the Claude Code plugin system, not Codex-style files. Only scaffold Codex files when the user explicitly asks to add Codex support (see the worked example below).
How Codex CLI discovers instructions (AGENTS.md)
Codex builds one instruction chain per run by concatenating files from two layers, joined by blank lines — it does NOT pick a single "winning" file:
- Home layer (
~/.codex, or$CODEX_HOME): readsAGENTS.override.mdif present, elseAGENTS.md. First non-empty file at this level only. - Project layer: from the project root (usually the git root) walking down to the current
working directory, in each directory it takes at most one of:
AGENTS.override.md, thenAGENTS.md, then any name inproject_doc_fallback_filenames(config-driven). All matched files are concatenated root-first.
A nested AGENTS.md in a subdirectory adds to (does not replace) the root one — closer files
come later in the concatenation, so they refine rather than override.
Rough Claude Code analogues (not 1:1 — see Gotchas):
CLAUDE.md↔AGENTS.md(repo-wide instruction file).claude/agents/*.md↔ persona/role blocks written inline inAGENTS.md.claude/skills/*/SKILL.md↔.agents/skills/*/SKILL.md
How Codex discovers skills
Codex reads skills from repository, user, admin, and system locations. For a repo, it scans
.agents/skills in every directory from the current working directory up to the repo root.
Each skill is a folder with a SKILL.md:
.agents/skills/
skill-name/
SKILL.md # YAML frontmatter (name, description) + instructions
Codex uses the same progressive-disclosure model as Claude Code: it loads each skill's name,
description, and file path up front, and only reads the full SKILL.md body when it decides to
use that skill. So a good Codex description is a routing rule, exactly as in this plugin.
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.
- 1mo ago First seen · 121 lines · 118 tokens per session scan A 7546640d17ca
Codex Framework is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 1,754 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…