subagent-mcp-installer

subagent-mcp-installer is a skill for Claude Code, Codex from Heretyc/subagent-mcp. It costs 0 tokens per session (1,924 once invoked), scanned B, original, Apache-2.0.

A procedure for installing and registering the subagent-mcp add-on for Claude Code CLI and Codex CLI. It covers the MCP server, automatic per-turn hooks, and the instruction files they use.

In plain words
What is it for?
Use it to deploy the add-on permanently, register it with supported coding-agent tools, and verify that the installation works.
Why use it?
It ensures the installation lives in a stable location and remains usable after a repository, temporary folder, or development checkout changes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: UserPromptSubmit hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the subagent-mcp plugin — 8 skills, 3 hooks, 1 MCP server shipped together

Good fit Use it to deploy the add-on permanently, register it with supported coding-agent tools, and verify that the installation works.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heretyc/subagent-mcp/subagent-mcp-installer
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 Heretyc/subagent-mcp --skill subagent-mcp-installer
Clone the repo
git clone --depth 1 https://github.com/Heretyc/subagent-mcp

Made for: Claude Code, Codex.

Or install subagent-mcp, the plugin that ships this one along with the rest of its 8 skills, 3 hooks, 1 MCP server.

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 subagent-mcp-installer

README.md
[![agentmods](https://agentmods.dev/badge/skills/heretyc/subagent-mcp/subagent-mcp-installer.svg)](https://agentmods.dev/skills/heretyc/subagent-mcp/subagent-mcp-installer)
Your own site
<a href="https://agentmods.dev/skills/heretyc/subagent-mcp/subagent-mcp-installer"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/subagent-mcp-installer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.01924
Opus 5 $0.00000 $0.00962
Sonnet 5 $0.00000 $0.00385
Haiku 4.5 $0.00000 $0.00192

Measured 7d ago against content hash 5034d5866499, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

subagent-mcp-installer 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/deploy.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

| Codex CLI | yes (`~/.codex/config.toml`) | yes (`SessionStart` + `UserPromptSubmit`) | `references/codex-cli.md` |
skills/subagent-mcp-installer/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

subagent-mcp Installer

Deploy the subagent-mcp addon : the MCP stdio server plus the per-turn orchestration-mode hooks and their directive assets : to a permanent, repo-decoupled location, then register it with each supported vendor using that vendor's official, standards-compliant mechanism.

Input = the host machine + which vendors are present (Claude Code CLI, Codex CLI). Output = a working, verified install that does NOT reference the dev repo, a worktree, or any temp path.

This skill is the authoritative install SOP. It supersedes the absolute-path-to- repo examples in docs/install/* (those point at the build tree; this ships a decoupled copy). When they disagree, this skill wins.

Non-negotiable rules

  1. Permanent location only. Install to the global npm package dir (npm root -g<root>/@heretyc/subagent-mcp) or another stable, user-owned dir. NEVER install from or point config at: a git worktree, %TEMP%, /tmp, /TMP, $TMPDIR, os.tmpdir(), a Downloads folder, or the live dev checkout. See references/locations.md for the full forbidden list and the rationale (these get garbage-collected, moved, or rebuilt under you).
  2. Ship ALL parts. Server (dist/index.js), Claude hooks (dist/hooks/orchestration-claude.js, orchestration-claude-pretool.js), Codex hook (orchestration-codex.js), the ruleset scaffold (dist/advanced-ruleset.py), the global config (dist/global-subagent-mcp-config.jsonc), and the directives/ dir must all land in the install. Required directive assets include orchestration, carryover, reminder, and short pointer files for every supported hook host. The compiled hooks resolve their directive assets via ../../directives, so directives/ must sit beside dist/ in the install root. A user-edited dist/advanced-ruleset.py is NEVER overwritten on update: deploy.mjs snapshots it before npm install -g and restores it after. dist/global-subagent-mcp-config.jsonc is the sole canonical user-editable retained config; the same snapshot/restore mechanism preserves user edits to the global config across installs and updates.
  3. Standards-compliant per vendor. Use each vendor's official registration path and config schema, verbatim from the specs in references/compliance.md. No bespoke shims.
  4. Decoupled from source. A repo edit must NOT change a live install until the operator re-runs the install. npm pack + npm install -g (a copy, not a symlink : never npm link) guarantees this.
  5. Idempotent + reversible. Re-running is safe; back up any user config file before editing it; repoint/uninstall is documented.

Read the full file on GitHub · 123 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. 7d ago First seen · 123 lines · 0 tokens per session scan B 5034d5866499

Subscribe to this mod's changes

subagent-mcp-installer is a skill published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,924 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

planflow

Draft a plan and get it approved as an editable flowchart in the user's browser before executing. Use when the user asks to plan a task with PlanFlow, or wants to review, edit, or approve a plan before any code changes are made.

davejj1530/planflow-greenlight · 53 tokens

chief-revenue-officer

Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…

cbrock84/headcount · 80 tokens

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens

seo-strategy

Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…

cbrock84/headcount · 74 tokens

financial-statement-analysis

Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…

cbrock84/headcount · 93 tokens

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens