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 agentmods add commands/agent-marketplace-kit/cli/initgit clone --depth 1 https://github.com/AGent-marketplace-KIT/cliWhat 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 | $0.00897 |
| Opus 5 | $0.00006 | $0.00449 |
| Sonnet 5 | $0.00002 | $0.00179 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agmk init
Scaffold a new, push-ready plugin marketplace (git-first) — or, with --plugin,
a standalone plugin with no marketplace around it.
agmk init [dir] [options]
Arguments
| Argument | Description |
|---|---|
[dir] |
Target directory. Defaults to the current directory. Created if missing. |
Options
| Option | Description |
|---|---|
-n, --name <name> |
Marketplace (or plugin) name, kebab-case. Defaults to the directory name. |
-o, --owner <owner> |
Owner / author name. |
-e, --email <email> |
Owner email. |
-d, --description <text> |
Marketplace (or plugin) description. |
-r, --repo <url> |
Git remote URL (any forge). Used to fill in install docs and team settings. |
--ci <ci> |
CI workflow: github | gitlab | none. Default github. |
--agents <list> |
Comma-separated target agents. Default claude-code,copilot. |
--plugin [template] |
Scaffold a standalone plugin in [dir] instead of a marketplace. |
-y, --yes |
Non-interactive: accept defaults for anything not passed. |
Known agent ids for --agents: claude-code, copilot, codex, cursor,
gemini, opencode, windsurf, kiro. Unknown ids are ignored with a warning.
What it scaffolds (marketplace mode)
<dir>/
├── .claude-plugin/marketplace.json # $schema, name, owner, metadata{version:"1.0.0", pluginRoot:"./plugins", targets}, plugins:[]
├── plugins/.gitkeep
├── README.md # install + team sections composed from --agents
├── AGENTS.md # repo context for agents
├── examples/team-settings.json # extraKnownMarketplaces block
├── .github/workflows/validate.yml # or .gitlab-ci.yml (--ci gitlab); none with --ci none
└── .gitignore
- Runs
git initautomatically (unless already inside a repo). - Interactive mode additionally offers to add a starter plugin (runs
agmk addfor you). - Rejects the reserved marketplace names.
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 · 89 lines · 12 tokens per session scan A ce37ffd0ad23
init 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 897 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.
Other commands, from other repositories
annotate-plan
Draft a plan and open it in the annotator UI for user review.
docs
Command "docs" from tilework-tech/nori-skillsets, covering noridoc: commands, how it fits into the larger codebase, core implementation and things to know.
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…
event-loop
You are processing one pending l00prite event. Events are protocol objects, not vendor-specific automation commands.
respond-to-review
You are responding to one review-related l00prite event. Treat .l00prite/ as the shared source of truth across agents.
resume-loop
You are resuming a l00prite-managed project. Treat .l00prite/ as the shared source of truth across Claude, Codex, GPT, Gemini, and future agents.