What makes tokei-agent notable?

1.2K downloads. Trust evidence available

How should tokei-agent be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

tokei-agent

Tokei (tokei.io) is a pre-launch, waitlist and giveaway platform — launch pages, competition giveaways, sweepstakes, referral and viral-loop campaigns, Product Hunt launch drives, Gleam-style and KickoffLabs-style entry pages. This CLI controls them from the command line — list, clone, update, publish and unpublish pages, upload images and video, set prizes, reward tiers and deadlines, restyle pages, and read stats, leaderboards, top referrers, signups, survey responses, winner selections and the webhook event catalog, plus manage webhooks (all 5 events) — all via the Tokei v1 REST API.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

0.3.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 0.3.6release · observed Sep 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17f49saxv9xfh8dt4h21w9pgs8ax0fm:tokei-agent

Install using `clawhub skill install s17f49saxv9xfh8dt4h21w9pgs8ax0fm:tokei-agent` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/gilesdawe/tokei-agent before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-gilesdawe-tokei-agent/snapshot"

Documentation

CLAWHUB

151,250 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: tokei-agent
description: Tokei (tokei.io) is a pre-launch, waitlist and giveaway platform — launch pages, competition giveaways, sweepstakes, referral and viral-loop campaigns, Product Hunt launch drives, Gleam-style and KickoffLabs-style entry pages. This CLI controls them from the command line — list, clone, update, publish and unpublish pages, upload images and video, set prizes, reward tiers and deadlines, restyle pages, and read stats, leaderboards, top referrers, signups, survey responses, winner selections and the webhook event catalog, plus manage webhooks (all 5 events) — all via the Tokei v1 REST API.
homepage: https://tokei.io/agent
metadata: {"openclaw":{"emoji":"⏱️","requires":{"bins":[],"env":["TOKEI_API_KEY"]}}}
---

# tokei-agent

`tokei-agent` is a zero-dependency CLI for the Tokei v1 REST API (`https://tokei.io/api/v1`). Every command prints JSON to stdout, so pipe it to `jq` or parse it directly.

## Install tokei-agent if it isn't already there

```sh
npm install -g tokei-agent
# or run it without installing:
npx tokei-agent --help
```

Requires Node 22+. npm release: https://www.npmjs.com/package/tokei-agent — official website: https://tokei.io — agent docs: https://tokei.io/agent — API reference: https://tokei.io/docs/api

---

## ⚠️ Four hard rules (read first)

**Rule 1 — Run `tokei-agent me` before anything else.** It proves the key is live and reports the account's **plan**. API access requires an active subscription or lifetime plan — **trial accounts get `403` on every command**, so a whole workflow can fail on its first call for a reason no other command explains.

> `me` does **not** report the key's scope. There is no way to read a key's scope from the API — you discover a read-only key by getting `403 FORBIDDEN` on your first write. If the task involves changing anything, ask the human up front whether their key is read+write.

**Rule 2 — Every media URL you write to a page MUST come from `tokei-agent media:upload`.** Raw filesystem paths (`hero.png`) and third-party URLs (`https://example.com/hero.png`) are **rejected** — the seven media fields on `pages:update` are guarded by a closed host allowlist that only accepts the app's own storage (and `res.cloudinary.com`). Always:

```sh
HERO=$(tokei-agent media:upload ./hero.png | jq -r '.data.public_url')
tokei-agent pages:update "$PAGE_ID" --image-video "$HERO"
```

Every `--image-video` / `--og-image` / `--background-image` example below assumes a `public_url` obtained this way — never a local file.

**Rule 3 — List fields replace wholesale; always read before you write.** `prizes` (max 20) and `reward_thresholds` (max 50) are **not** merged — whatever array you send becomes the entire list, so sending one prize deletes the other nineteen. The pattern is always `pages:get` → modify the array → `pages:update` with the complete list.

**Rule 4 — Get explicit human approval before any action that emails people or changes anything public.** Publishing a page,

README.md

# tokei-agent

Control your [Tokei](https://tokei.io) pre-launch and waitlist campaigns from the command line — and from AI agents like Claude Code and OpenClaw. Wraps the Tokei v1 REST API with JSON-only output, zero runtime dependencies.

## Install

```sh
npm install -g tokei-agent
# or run without installing:
npx tokei-agent --help
```

Requires Node 22+.

### Claude Code

Install it as a plugin and the `tokei-agent` skill comes with it — Claude then
knows the whole command surface without being told:

```
/plugin marketplace add gilesdawe/tokei-agent
/plugin install tokei-agent@tokei
```

Set `TOKEI_API_KEY` (see [Quick start](#quick-start)) and you're done. The CLI
itself still runs via `npx`, so there is nothing else to install.

## Quick start

1. Create an API key at [tokei.io](https://tokei.io) → Dashboard → Settings → API Keys. Pick **read-only** unless you need to change things; API access requires an active subscription or lifetime plan.

2. Export it — the syntax differs by shell:

```sh
export TOKEI_API_KEY=tokei_k_...          # bash / zsh
```

```fish
set -x TOKEI_API_KEY tokei_k_...          # fish
```

```powershell
$env:TOKEI_API_KEY = "tokei_k_..."        # PowerShell
```

3. Try it:

```sh
tokei-agent me                       # verify the key, see plan + API usage
tokei-agent pages:list --status active
tokei-agent stats <contestId>        # analytics for one page
```

Every command prints JSON to stdout with a top-level `rate_limit` object. Exit codes: `0` success, `1` API/network error, `2` usage error (JSON on stderr).

> **Interactive output (0.3.1+).** When stdout is an interactive terminal, the CLI renders a banner and a human-readable summary instead of raw JSON. When stdout is a pipe, a redirect, CI, or the `mcp` transport, it prints exactly the JSON it always has — so agents, scripts and MCP clients are unaffected. Set `TOKEI_OUTPUT=json` to force JSON at a terminal too; `NO_COLOR` disables colour and animation, and `TOKEI_NO_ANIM=1` keeps the colour but stops the movement.

> **Known issue — exit codes on Node 24 / Windows (fixed in 0.3.0).** On 0.2.2 and earlier the CLI could print its correct JSON output and then abort during process exit, corrupting the exit code (`$LASTEXITCODE` read `-1073740791` / `0xC0000409` on success and failure alike). On an affected version, judge a run by the JSON on stdout, not by the exit status — or upgrade. (Historical labelling slip: the 0.3.0 tarball misreported `--version` as `0.2.2`; 0.3.1+ reports correctly.)

## Commands

Read (any key):

| Command                    | Does                                                        |
| -------------------------- | ----------------------------------------------------------- |
| `me`                       | Verify the key; account, plan, API usage                    |
| `pages:list`               | List pages — `--status`, `--mode`, `--page`, `--per-page`   |
| `pages:get <contestId>`    | One page in full (prizes, reward tiers, pub

_meta.json

{
  "ownerId": "kn71v6w9gadrqg1bvex24zx4ex8aw3qd",
  "slug": "tokei-agent",
  "version": "0.3.6",
  "publishedAt": 1788552983598
}

CHANGELOG.md

# Changelog

All notable changes to `tokei-agent`. Dates are the npm publish times.

This file was seeded on 2026-08-02, after 0.3.2 shipped, by reconstructing the
history from `npm view tokei-agent time` and the commits that touched `cli/`.
Entries before 0.3.3 are therefore summaries written after the fact; entries
from 0.3.3 on are written as part of the release.

The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
This package is pre-1.0: minor versions may carry breaking changes, though none
has so far.

## [Unreleased]

## [0.3.5] — 2026-08-28

### Fixed

- **MCP tool calls no longer forward undeclared arguments.** `callTool` built the
  request body as `{ ...fixedBody, ...args }` and validated only that *required*
  arguments were present, so any extra field a caller invented rode through to the
  API. Because `PATCH /api/v1/contests/{id}` replaces `prizes` wholesale, a call of
  `pages_publish { contest_id, prizes: [] }` **wiped the page's prize list** — under
  a tool annotated `destructiveHint: false`. Arguments are now allowlisted against
  the tool's own `inputSchema.properties` before the merge; undeclared fields are
  dropped, and the tool result now names the ones it ignored rather than
  discarding them in silence. Declared arguments still win over `fixedBody`.

  One documented field was caught by this and is declared as part of the same
  release: `entries_create` accepted `marketing_consent`
  (`docs/using-custom-apis.md`) without advertising it, so the allowlist would
  have dropped it. See Added below.
- **`entries_create` was silently discarding `marketing_consent`.** The v1 route
  accepts it and the field gates whether an entrant is ever synced to the
  creator's connected email provider, so an import of consented entrants would
  have returned 201 on every row and synced none of them.

### Added

- `entries_create` declares `marketing_consent`. Set it to `true` only when the
  participant genuinely gave marketing consent elsewhere; it records the consent
  and its timestamp, and is what enables the email-provider sync.

### Changed

- `pages_update`'s description now states that `status` is not settable there and
  points at `pages_publish` / `pages_unpublish`. `status` stays undeclared on
  purpose — `pages_publish` enforces a future-`end_date` check that a raw
  `status: "active"` would bypass.
- `webhooks_delete` now declares `idempotentHint: true`, and its description states
  that the subscription's queued and historical `webhook_deliveries` rows are
  deleted with it (`ON DELETE CASCADE`), so past delivery attempts are not
  retrievable afterwards.
- The MCP server instructions and the `pages_unpublish` description are reworded
  from instructing the agent ("slow down", "Tell your user this…") to describing
  what the API does. No behavioural change.

## [0.3.4] — 2026-08-21

### Added

- `pages:update --template simple` — the Custom template: bare structural
  markup the creator styles enti

skill-card.md

## Description:

tokei-agent lets agents and CLI users manage Tokei waitlist, launch, giveaway, referral, webhook, media, and analytics workflows through the Tokei v1 REST API.

This skill is ready for commercial/non-commercial use.

## Publisher:

[gilesdawe](https://clawhub.ai/user/gilesdawe)

### License/Terms of Use:

MIT

## Use Case:

Developers and campaign operators use this skill to let agents inspect and manage Tokei pre-launch, waitlist, giveaway, referral, media, analytics, and webhook workflows from CLI or MCP surfaces.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can give an agent high-impact control over Tokei account resources, including publishing pages, creating webhooks, adding entries, and uploading media.

Mitigation: Use a pinned package version, prefer read-only and short-lived Tokei keys, and require explicit human approval before write actions, public changes, email-affecting actions, or unattended media_upload calls.

Risk: Credentials and API destination choices can expand account exposure, especially when TOKEI_API_URL is overridden.

Mitigation: Keep TOKEI_API_KEY scoped to the task, rotate or expire keys after use, and avoid setting TOKEI_API_URL unless the destination is fully trusted.

Risk: API responses and uploaded files can include personal or campaign-sensitive data that may be exposed through agent transcripts, logs, or public campaign assets.

Mitigation: Review command outputs before sharing, limit logging of entrant data and survey responses, and inspect local files before uploading them as campaign media.

## Reference(s):

- [Tokei Agent Docs](https://tokei.io/agent)
- [Tokei API Reference](https://tokei.io/docs/api)
- [Tokei OpenAPI Specification](https://tokei.io/openapi.json)
- [tokei-agent npm Package](https://www.npmjs.com/package/tokei-agent)
- [ClawHub Skill Page](https://clawhub.ai/gilesdawe/skills/tokei-agent)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown guidance with shell commands; commands return JSON from the Tokei API.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires TOKEI_API_KEY; write workflows may require a read+write key and explicit human approval.]

## Skill Version(s):

0.3.6 (source: release evidence, package.json, server.json)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.