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 skills add S3YED/appie-kit --skill clark-workgit clone --depth 1 https://github.com/S3YED/appie-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/s3yed/appie-kit/clark-work)<a href="https://agentmods.dev/skills/s3yed/appie-kit/clark-work"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/clark-work/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s3yed/appie-kit/clark-work"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/clark-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00048 | $0.01255 |
| Opus 5 | $0.00024 | $0.00628 |
| Sonnet 5 | $0.00010 | $0.00251 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
clark-work scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$DASH/api/agent/work" \ How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clark Work (agent lane)
The customer's tasks live in Clark Work on the dashboard (dash.getclark.app). As the customer's own agent you can read your customer's work, move tasks through their statuses, comment on them, and create your own projects and tasks there.
Identity and endpoint (never hardcode)
Your box already carries its own credentials. Source them instead of copying secrets:
CLARK="${CLARK:-$HOME/.clark}"
. "$CLARK/heartbeat.env" # provides APPIE_ID, APPIE_SECRET, APPIE_HEARTBEAT_URL
DASH="${APPIE_HEARTBEAT_URL%/api/appie/heartbeat}" # the dashboard origin
Call every action as POST $DASH/api/agent/work with two headers:
-H "X-Appie-Id: $APPIE_ID" -H "X-Appie-Secret: $APPIE_SECRET"
and a JSON body that describes the action. Never send a userId or
agentReference in the body. The dashboard derives your customer from your box
identity. A box can only ever touch its own customer's workspace, so these
calls are safe by construction.
Actions
list_work — read all projects + tasks
curl -s -X POST "$DASH/api/agent/work" \
-H "X-Appie-Id: $APPIE_ID" -H "X-Appie-Secret: $APPIE_SECRET" \
-H "Content-Type: application/json" \
-d '{"action":"list_work"}'
Returns { workspace, projects, items }. Each item has id, projectId,
title, description, status, priority, dueAt, createdAt, updatedAt.
create_project — start a new project
curl -s -X POST "$DASH/api/agent/work" \
-H "X-Appie-Id: $APPIE_ID" -H "X-Appie-Secret: $APPIE_SECRET" \
-H "Content-Type: application/json" \
-d '{"action":"create_project","name":"Q3 campaign","description":"optional"}'
Returns { project } with its id.
create_item — add a task to an existing project
curl -s -X POST "$DASH/api/agent/work" \
-H "X-Appie-Id: $APPIE_ID" -H "X-Appie-Secret: $APPIE_SECRET" \
-H "Content-Type: application/json" \
-d '{"action":"create_item","projectId":"<project-id>","title":"Draft newsletter","description":"optional","priority":"medium","status":"todo"}'
Statuses: backlog, todo, in_progress, in_review, done, cancelled.
Priorities: none, low, medium, high, urgent.
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.
- 5d ago First seen · 110 lines · 48 tokens per session scan A 37464edf0a39
clark-work is a skill published in the GitHub repository S3YED/appie-kit (8 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 1,255 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
scaffold
Create a new Next.js or Astro project on the bundled Cloudflare Workers stack with pnpm, Biome and Tailwind. Use for an empty target directory; skip existing applications and requests for a different stack.
clone-website
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a…
animation-patterns
Framer Motion patterns, page transitions, skeleton loading, scroll-linked animations, and gesture-based interactions for React.
component-library-patterns
Design system token management, component API design, Storybook, and visual regression testing patterns.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.