A command that creates the plugin registries used by Codex and Cursor from the main catalogue. A registry is the file those tools read to find installable plugins.

Use it after catalogue or plugin-manifest changes, or in continuous integration to verify that generated Codex and Cursor files have no drift.

It keeps generated installation files aligned with the canonical catalogue and can detect when committed files are out of date without changing them.

build — Command by AGent-marketplace-KIT

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 commands/agent-marketplace-kit/cli/build

Clone the repo

git clone --depth 1 https://github.com/AGent-marketplace-KIT/cli

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 555 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00555
Opus 5	$0.00006	$0.00278
Sonnet 5	$0.00002	$0.00111
Haiku 4.5	$0.00001	$0.00056

Measured yesterday against content hash 0b5361082db9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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 yesterday.

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.

docs/commands/build.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agmk build

Generate the committed registries that tier-2 agents (OpenAI Codex, Cursor) install from, derived from the canonical catalog. Native agents (Claude Code, GitHub Copilot) need no build.

agmk build [options]

Options

Option	Description
`--target <list>`	Comma-separated tier-2 targets to build. Default: the tier-2 targets in `metadata.targets`.
`--check`	Verify generated artifacts are up to date; non-zero exit on drift (for CI). Writes nothing.

Buildable targets: codex, cursor. Other ids are ignored with a warning.

What it generates

Codex (codex):

.agents/plugins/marketplace.json                 # registry: object sources { source:"local", path }, policy, category
plugins/<name>/.codex-plugin/plugin.json         # per-plugin manifest mirror

Cursor (cursor):

.cursor-plugin/marketplace.json                  # registry: string sources, same shape as the Claude catalog
plugins/<name>/.cursor-plugin/plugin.json        # per-plugin manifest mirror

Both derive entirely from .claude-plugin/marketplace.json and each plugin's .claude-plugin/plugin.json. Commit the generated files so consumers can install.

Behavior

With no --target, builds the tier-2 targets recorded in metadata.targets. If there are none, it prints a hint and does nothing.
Generation is opt-in: run agmk build once to enable a target. After the first build, agmk add, agmk bump, and agmk sync refresh the already-built registries automatically, so they never drift.
--check compares the on-disk files to what would be generated and reports missing: / stale: paths, exiting non-zero if any differ — the generated CI workflows run this.

Examples

agmk build                          # build the targets in metadata.targets
agmk build --target codex,cursor    # build specific targets
agmk build --check                  # CI gate: fail if a committed registry is stale

Read the full file on GitHub · 68 lines

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.

yesterday First seen · 68 lines · 12 tokens per session scan A 0b5361082db9

Subscribe to this mod's changes

build is a command published in the GitHub repository AGent-marketplace-KIT/cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 555 once invoked, about $0.0001 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.

Writing and docs agent-skills agentic-ai coding-agent marketplace scafolding

annotate-plan

Draft a plan and open it in the annotator UI for user review.

ndom91/open-plan-annotator · 14 tokens

docs

Command "docs" from tilework-tech/nori-skillsets, covering noridoc: commands, how it fits into the larger codebase, core implementation and things to know.

tilework-tech/nori-skillsets · 0 tokens

build-loop

Planning Mode — scaffold a target project's l00prite/ folder (CLAUDE.md blueprint, AGENTS.md, .l00prite memory, universal loop prompts), root pointer files, vendor adapters, and a skeleton repo from a project idea. Stops after scaffolding; --execute hands off to Execution Mode only through execute-loop's confirmed…

jackofall1232/l00prite · 70 tokens

build