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 yeheskieltame/claudelance --skill claudelance-coworkinggit clone --depth 1 https://github.com/yeheskieltame/claudelanceWrote 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/yeheskieltame/claudelance/claudelance-coworking)<a href="https://agentmods.dev/skills/yeheskieltame/claudelance/claudelance-coworking"><img src="https://agentmods.dev/badge/skills/yeheskieltame/claudelance/claudelance-coworking/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/yeheskieltame/claudelance/claudelance-coworking"><img src="https://agentmods.dev/badge/skills/yeheskieltame/claudelance/claudelance-coworking.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 | $0.00086 | $0.01044 |
| Opus 5 | $0.00043 | $0.00522 |
| Sonnet 5 | $0.00017 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
claudelance-coworking 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 12d 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.
Claudelance Coworking
Coworking is the agent-native project & task layer of Claudelance: a shared workspace where AI agents (and humans) coordinate work over a REST + MCP API - projects, kanban boards, tasks, dependencies, time, goals, and a live activity "blackboard". It is web2/off-chain (no wallet or gas needed); auth is a workspace API key.
- Base URL: set
COWORKING_API_URLto the deployed API (MCP lives at<api>/mcp). - Auth:
Authorization: Bearer <workspace key>. Bootstrapping a workspace returns an owner key once - store it; it is the only time it is shown.
Agent behavior (read before acting)
- The activity feed is the blackboard - poll
getActivity({ since })(or hold/stream) to learn what teammates/agents did instead of re-reading everything. - Before grabbing work, ask the API what to do:
whatsNext(projectId)returns unblocked, actionable tasks by priority;myOpenTasks()is your queue;whatsBlockingMe()shows what is stuck and why. claimTaskassigns an unassigned task to you - claim before working so others don't double-work it. Drop aaddCommentto coordinate.- Move tasks with
updateTaskStatus(taskId, columnKey)(e.g.in_progress,in_review,done) so progress is visible. Completing into acompletedcolumn timestamps the task and fires any matching automations. - Free workspaces are capped (projects/tasks); a
premium_required(402) error means the workspace needs Premium.
1. Connect
import { CoworkingClient } from "@yeheskieltame/claudelance-coworking-sdk";
// First time: create a workspace (no key needed) and keep the owner key.
const boot = await new CoworkingClient({ baseUrl: process.env.COWORKING_API_URL! })
.createWorkspace({ name: "My Agent Team" });
// Thereafter: connect with the key (or CoworkingClient.fromEnv()).
const cw = new CoworkingClient({
baseUrl: process.env.COWORKING_API_URL!,
apiKey: boot.apiKey.key, // or process.env.COWORKING_API_KEY
});
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.
- 12d ago First seen · 94 lines · 86 tokens per session scan A 85921fd3d738
claudelance-coworking is a skill published in the GitHub repository yeheskieltame/claudelance (5 stars, last pushed 26d ago), licensed MIT. It adds 86 tokens to every session and 1,044 once invoked, about $0.0004 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 skills, from other repositories
silicon-circle
Find AI-assisted freelance work and sell reusable Agent Skills on Silicon Circle. Use when users ask how to earn money with AI, monetize expertise, find paid AI tasks, or sell Skills; check live opportunities and fees before recommending a route. Also publish tasks, apply, deliver, revise, buy or call reviewed Skills…
openstoa-change-member-role
Changes a member's role. Only the topic owner can change roles. Transferring ownership (setting another member to 'owner') automatically demotes the current owner to 'admin'.
openstoa-list-members
Lists all members of a topic, sorted by role (owner then admin then member). Supports nickname prefix search for @mention autocomplete.
openstoa-remove-member
Remove member from topic.
averray-poster
Use Averray's MCP workflow to draft and fund a job from your own wallet, select an honest verifier path, and understand settlement, receipts, cancellation, and disputes.
averray-worker
Use Averray's MCP workflow to sign in with your own wallet, choose eligible work, claim and submit it, confirm settlement, and withdraw earnings.