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/addgit 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 | $0.00016 | $0.01037 |
| Opus 5 | $0.00008 | $0.00518 |
| Sonnet 5 | $0.00003 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
add 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 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agmk add
Register a plugin in the marketplace catalog and refresh the README table and
AGENTS.md. Run it from anywhere inside the marketplace.
agmk add [template|spec] [name] [options]
If you omit the spec and/or the name, agmk prompts for them interactively.
Arguments
| Argument | Description |
|---|---|
[template|spec] |
A built-in template name, a local path, or a remote git source. See resolution. |
[name] |
Plugin name, kebab-case. |
Options
| Option | Description |
|---|---|
-d, --description <text> |
One-line plugin description (skips the prompt). |
--vendor |
Clone the remote source and scaffold from its files, instead of referencing it. |
--ref <ref> |
Branch or tag to pin a referenced remote source to. |
--sha <sha> |
Commit hash (full 40 hex) to pin a referenced remote source to. |
How the spec is resolved
agmk decides what to do from the shape of the spec:
| Spec | Mode | Result |
|---|---|---|
skill / command / agent / hook / mcp |
scaffold | built-in template → plugins/<name>/, source: "./plugins/<name>", version: "0.1.0" |
./dir, /abs/dir, path:<dir> |
scaffold | local template directory → plugins/<name>/ |
owner/repo, gh:…, gl:…, git URL, …//subdir |
reference (default) | object source (github / url / git-subdir); nothing cloned |
any remote spec + --vendor |
vendor | clone + scaffold into plugins/<name>/, source: "./plugins/<name>" |
A remote git source is referenced by default — no clone, no files copied. The
agent fetches it at install time. Add --vendor to copy the upstream files into
your repo instead.
--vendorneeds an explicitgh:/gl:shorthand or a git URL. A bareowner/repoworks only for referencing.
See the full grammar on Template & source spec.
Behavior
- Fails if a plugin with the same name already exists, or if
nameis not kebab-case. - Reference mode writes an object
source(optionally pinned with--ref/--sha) and runs an internalsync. Nothing is cloned. - Scaffold / vendor mode renders the template (
.tplfiles get{{pluginName}},{{pluginTitle}},{{description}},{{authorName}}in contents and names; executable bits preserved), forces the manifestnameto match, registers a relativesource, and runs an internalsync. - After
add, if you target Codex/Cursor, runagmk buildonce so the new plugin is installable there (subsequent adds refresh it automatically).
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.
- 2d ago First seen · 94 lines · 16 tokens per session scan A b91c76eb99e9
add is a command published in the GitHub repository AGent-marketplace-KIT/cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,037 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.