An installer for the custom agent files that SpecKit Pro expects Codex to use. It copies the bundled TOML configuration files into the Codex agents directory and verifies them.

It is for installing, refreshing, repairing, or verifying SpecKit Pro's Codex subagents.

It removes the manual work of copying and checking the required agent definitions. It also tells the user when Codex must be restarted for the agents to load.

install — Skill for Claude Code and Codex by racecraft-lab

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.

Any agent

npx skills add racecraft-lab/racecraft-plugins-public --skill install

Clone the repo

git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-public

Made for: Claude Code, Codex.

Or install speckit-pro, the plugin that ships this one along with the rest of its 13 skills, 16 agents, 3 hooks, 3 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/install/github.svg)](https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/install)

Your own site

<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/install"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/install/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/install"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,583 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 134
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Excessive Agency · line 200
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 203
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.02583
Opus 5.5	$0.00024	$0.01033
Sonnet 5.5	$0.00012	$0.00517
Haiku 4.5	$0.00006	$0.00258

Measured 1mo ago against content hash 1da404ecda79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

install 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.

speckit-pro/codex-skills/install/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecKit Install

Installed Runtime Contract

Before any runner helper call, follow Installed runner transport. Invoke [resolved_python, "<plugin-root>/scripts/run-speckit-pro.py"] from the current project using the root of this loaded plugin.

Scope

Use this skill when the user wants to install, refresh, repair, or verify the Codex custom subagents that ship with this plugin. This skill exists only for the Codex runtime. It does not manage Claude Code agents, Claude marketplace metadata, or Claude commands.

The bundled source of truth lives in the plugin at:

codex-agents/*.toml

The default user-scope Codex destination is the agents directory of the Codex home that Codex itself reads:

$CODEX_HOME/agents/ when CODEX_HOME is set, else ~/.codex/agents/

If the user explicitly asks for project scope, use .codex/agents/ in the current project. Arbitrary destinations are rejected. Otherwise install to the default user-scope path above.

What This Skill Installs

The runner-owned catalog determines which bundled agents are required or optional. The response field data.agent_files supplies the concrete filenames for the invocation. The installer fails before planning when required source templates are missing, and route-aware mode may omit the optional helper only when no-helper continuation validates.

These files follow the official Codex subagent format: one standalone TOML file per custom agent, with required name, description, and developer_instructions fields plus Codex config such as sandbox_mode.

Operator note: an agent file's sandbox_mode is advisory; a spawned agent keeps the parent's sandbox. Once you trust the plugin's hooks, its PreToolUse agent-policy hook denies a read-only agent's apply_patch edits and a broker-only agent's calls to MCP tools outside its allowlist. A hook cannot tell a shell write from a shell read, so a read-only agent's shell writes stay a rule of its instructions, and a read-only agent without a broker allowlist can still reach any MCP server you enable. To keep such an agent provably unable to write through MCP, curate write-capable MCP servers OUT at the profile/config level (enabled = false, or enabled_tools/disabled_tools).

Read the full file on GitHub · 254 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 400 B

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.

1mo ago Changed · +7 lines 1da404ecda79
1mo ago Changed b5c10e4f32e4
1mo ago Changed · +1 lines · +7 tokens per session 368ffab46b27
1mo ago Changed · +5 lines 2fcc0746dbf2
1mo ago Changed 0a059c3e470d
1mo ago Changed · +16 lines 5479043812c8
2mo ago Changed · -148 lines dd4070bbd73e
2mo ago First seen · 373 lines · 54 tokens per session scan A 96eac5d13235

Subscribe to this mod's changes

install is a skill published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 2,583 once invoked, about $0.0002 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 2026-09-04.

Building agents Claude Code Productivity claude-plugins mcp skills spec-driven-development

install next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
installracecraft-lab/racecraft-plugins-public	Skill	5	2d ago	MIT	A	61	Claude Code, Codex
agent-delegationyeisonrestrepo/code-conductor	Skill	18	today	MIT	A	39	Claude Code, Codex
memory-firstyeisonrestrepo/code-conductor	Skill	18	today	MIT	A	32	Claude Code, Codex
verbosityyeisonrestrepo/code-conductor	Skill	18	today	MIT	A	32	Claude Code
ask-firstonur-aslan/sdd	Skill	10	yesterday	MIT	A	17	Claude Code
grounded-modeonur-aslan/sdd	Skill	10	yesterday	MIT	A	18	Claude Code
routinesanthropics/claude-plugins-official	Skill	47k	today	Apache-2.0	A	45	Claude Code