Skills/ClawHub/tokei-agent

tokei-agent@0.3.9

VERIFIED· startup only

Publisher claims: "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." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gilesdawe · publishing for 30 daysInstalls 1,579Last detonated 39 min ago
$clawhub install tokei-agent
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What changed since 0.3.8

vet-skills diff tokei-agent 0.3.8 0.3.9

This version reaches for something 0.3.8 did not: 2 new hosts (tokei.io, x.com) · 1 new credential variable (TOKEI_API_KEY). Compared from the two recorded runs, not from source.

New hosts
tokei.io, x.com
New credential variables
TOKEI_API_KEY

0.3.9 was run further than 0.3.8 (startup only vs install only); some additions may be first observations rather than changes.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-22 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-PD70An/task/home/work/acme-api/.claude/skills/tokei-agent/dist/index.js' } Node.js v22.23.5
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:17 · npx invocation of non-well-known package — may execute untrusted codenpx tokei-agent --helpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/index.ts:544 · npx invocation of non-well-known package — may execute untrusted code// `npx tokei-agent --help` is line 1 of the README quickstart. renderBannerFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionSKILL.md:498 · File type combined with upload action — agent may exfiltrate local data files… ## `--data` semantics Write commands accept `--data '<json>'` or `--data @file.json` for the raw request body (must be a JSON object). Individual field flags are merged **on top of** `--data` — **flags win** on conflict. The merged body i…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:493 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add tokei --env TOKEI_API_KEY=tokei_k_... -- npx -y tokei-agent mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈13,439 tok
1 file · 26 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.