A catalog checker for marketplace files and plugins. It runs local checks and can also use Claude Code's official plugin validator when that command-line tool is installed.

Use it to check a marketplace catalog locally or as an automated build gate. The strict option also treats warnings from the official validator as errors.

It catches invalid JSON, naming problems, missing plugin files, broken sources, and version mismatches before they reach users. Its non-zero exit status can stop a continuous-integration build when errors are found.

validate — 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/validate

Clone the repo

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

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 422 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	$0.00011	$0.00422
Opus 5	$0.00005	$0.00211
Sonnet 5	$0.00002	$0.00084
Haiku 4.5	$0.00001	$0.00042

Measured yesterday against content hash a7dafa60f0fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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/validate.md · 55 lines

What it actually says

agmk validate

Validate the marketplace catalog. Runs agmk's local checks and, when the Claude Code CLI is installed, delegates to the official claude plugin validate.

agmk validate [options]

Options

Option	Description
`--strict`	Treat warnings as errors in the official validator (forwarded to `claude plugin validate --strict`).

What it checks

Local checks (always run):

marketplace.json is present and valid JSON;
marketplace and plugin names are kebab-case;
the name is not one of the reserved marketplace names;
every plugin source resolves (local sources point at an existing directory; remote sources are well-formed);
each local plugin has a .claude-plugin/plugin.json manifest;
the catalog version matches the manifest (no drift).

Official validation (when claude is on the PATH):

runs claude plugin validate and folds its findings in; --strict is forwarded.

Output & exit code

Prints each warning and error. On any error it prints a summary and exits non-zero — so agmk validate is a drop-in CI gate. On success it confirms the catalog is valid, noting [local checks only] if the official validator was not available.

Examples

agmk validate            # local checks + claude plugin validate if installed
agmk validate --strict   # warnings become errors in the official validator

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 · 55 lines · 11 tokens per session scan A a7dafa60f0fa

Subscribe to this mod's changes

validate is a command published in the GitHub repository AGent-marketplace-KIT/cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 422 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

validate