codex-knowledge-patch

A reference guide for Codex, the coding-agent application and its surrounding tools. It covers the desktop and command-line interfaces, approvals, sandboxing, MCP integrations, plugins, cloud tasks, collaboration, and session controls.

In plain words
What is it for?
Use it for Codex configuration, security settings, CLI execution, cloud tasks, plugins, remote connections, MCP servers, collaborative sessions, TUI controls, and troubleshooting.
Why use it?
It helps you use current settings and workflows correctly, including supported approval policies and ways to run, review, steer, or share agent work.

Skill for Claude CodeCodex

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 skills/nevaberry/nevaberry-plugins/codex-knowledge-patch
Any agent
npx skills add Nevaberry/nevaberry-plugins --skill codex-knowledge-patch
Clone the repo
git clone --depth 1 https://github.com/Nevaberry/nevaberry-plugins

Made for: Claude Code, Codex.

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,783 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00009 $0.01783
Opus 5 $0.00005 $0.00892
Sonnet 5 $0.00002 $0.00357
Haiku 4.5 $0.00001 $0.00178

Measured 2d ago against content hash e89b0c48ca43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-knowledge-patch scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Settings go to `~/.codex/config.toml` or the selected profile. `--search`
plugins/knowledge-patch/patches-claude/codex-knowledge-patch/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Knowledge Patch

Use this skill when working with the Codex desktop app, CLI, TUI, remote app server, MCP integrations, cloud tasks, plugins, or collaborative agent workflows.

Reference index

Reference Topics
app-and-collaboration.md Desktop platforms, projects, skills, automations, imports, browser and voice context, image review, iOS
security-and-configuration.md Approval and sandbox modes, flags, feature settings, search, login, policy checks, diagnostics, Windows behavior
remote-mcp-and-connectors.md Remote TUI security, app-server authentication, MCP, connectors, proxied WebSockets, plugin sign-in
cli-execution-and-cloud.md Scripted execution, resume and review, cloud tasks, plugin marketplaces, desktop launching
tui-and-session-controls.md Steering, prompt editing, themes, planning, conversation controls, status UI, background commands, subagents

Replace deprecated approval behavior

Choose among the supported untrusted, on-request, and never approval policies. on-failure is deprecated. --full-auto combines the workspace-write sandbox with on-request approvals. --yolo bypasses sandboxing and approval prompts, so reserve it for an externally isolated environment.

Read security-and-configuration.md before changing approval, sandbox, authentication, policy, or search settings.

Account for hosted Code Mode approvals

Since 0.144.0, Code Mode defaults to hosted mode. Every approval request causes an elicitation pause. The writes app-approval mode lets declared read-only app actions proceed without prompting but requires approval for writes.

Use interactive MCP authentication directly

Since 0.144.0, MCP tools may request interactive authentication without an experimental opt-in. App-server hosts may provide authentication at runtime, hosted login may redirect success to a hosted page, and long-running app sessions refresh expired authentication for the hosted codex_apps connector.

Read the full file on GitHub · 184 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 184 lines · 9 tokens per session scan B e89b0c48ca43

Subscribe to this mod's changes

codex-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 1,783 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/obsidian-mcp-server · 62 tokens

api-context

Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.

cyanheads/obsidian-mcp-server · 79 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/obsidian-mcp-server · 85 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/obsidian-mcp-server · 46 tokens

field-test

Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…

cyanheads/obsidian-mcp-server · 76 tokens

maintenance

Investigate, adopt, and verify dependency updates — with special handling for @cyanheads/mcp-ts-core. Captures what changed, understands why, cross-references against the codebase, adopts framework improvements, syncs project skills, and runs final checks. Supports two entry modes: run the full flow end-to-end, or…

cyanheads/obsidian-mcp-server · 75 tokens