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 ai-ecoverse/slicc --skill mcpgit clone --depth 1 https://github.com/ai-ecoverse/sliccWrote 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/ai-ecoverse/slicc/mcp)<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/mcp"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/mcp/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/ai-ecoverse/slicc/mcp"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/mcp.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 | $0.00065 | $0.00613 |
| Opus 5.5 | $0.00026 | $0.00245 |
| Sonnet 5.5 | $0.00013 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
mcp 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 13d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp
mcp add connects this cone to someone else's server. mcp --serve does the opposite: it publishes .jsh CLIs from this session as one server.
Publish CLIs
mcp --serve /workspace/skills/jira/jira.jsh
mcp --serve gh=/workspace/skills/github/scripts/gh.jsh
The first call prints one URL, https://<token>.sliccy.now/mcp. A later mcp --serve joins that same URL. name=path sets the tool prefix when two files would otherwise collide.
mcp --serve --list
mcp --serve --stop gh
mcp --serve --stop
--list prints the URL and the CLI names. --stop with a name drops that CLI and leaves the URL valid. --stop alone revokes the server.
Each call runs the script once. Calls for one CLI run one at a time. A call that passes the time budget returns an error and leaves the script running; the next call for that CLI waits until it exits. Tool names always carry the CLI prefix: jira_get, jira_help, jira_invoke, gh_pr_list. invoke takes { "argv": ["get", "PROJ-1"], "stdin": "optional" }. argv is one element per argument.
The other client signs in on that URL. Accept lets it run every CLI in the set, including each script's skill.token and the signed-in browser tabs. Adding a file after Accept asks again. Stopping one CLI does not.
The URL lasts while the publication does, including across reload. Tool calls need this session to be the leader. Discovery and token refresh still answer when it is away.
A script may print JSON on --mcp and exit 0 to name its own commands. Otherwise commands come from --help.
The publication file is /workspace/.mcp/served.json. That is not /workspace/.mcp/servers.json, which is the list of servers this cone connects to.
Connect to a server
mcp add https://example.com/mcp weather
mcp exposure weather direct
mcp invoke weather get-forecast --lat 51.5 --lon -0.12
mcp list
mcp delete weather
mcp exposure weather direct exposes that server's tools to the agent. The default keeps them inside a server-local QuickJS tool.
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.
- 13d ago First seen · 53 lines · 65 tokens per session scan A 04e03f5d0b18
mcp is a skill published in the GitHub repository ai-ecoverse/slicc (34 stars, last pushed 2d ago), licensed Apache-2.0. It adds 65 tokens to every session and 613 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
actionbook-scraper
Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.