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 Coldin04/Cyime --skill cyime-workspacegit clone --depth 1 https://github.com/Coldin04/CyimeWrote 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/coldin04/cyime/cyime-workspace)<a href="https://agentmods.dev/skills/coldin04/cyime/cyime-workspace"><img src="https://agentmods.dev/badge/skills/coldin04/cyime/cyime-workspace/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/coldin04/cyime/cyime-workspace"><img src="https://agentmods.dev/badge/skills/coldin04/cyime/cyime-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 193 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00038 | $0.02368 |
| Opus 5 | $0.00019 | $0.01184 |
| Sonnet 5 | $0.00008 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
cyime-workspace 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 9d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cyime Workspace
Use this skill to operate the user's Cyime workspace through MCP-first Markdown tools. Prefer MCP tools when the client supports MCP. Fall back to the REST Open API only when MCP is unavailable.
Connection
- MCP endpoint:
http://127.0.0.1:8080/api/v1/mcp - REST Open API root:
http://127.0.0.1:8080/api/v1/open - REST OpenAPI:
http://localhost:5173/openapi.json - Browser OAuth authorize URL:
http://127.0.0.1:8080/api/v1/auth/skill/oauth/authorize - Browser OAuth token URL:
http://127.0.0.1:8080/api/v1/auth/skill/oauth/token - Authentication: set
Authorization: Bearer <cyime_api_token>on every protected request. - Never reveal, repeat, log, or summarize the raw API token in chat output.
MCP Client Config Shapes
Different MCP clients wrap the same Cyime endpoint in different config shapes:
- MCP server map: use this when the client expects a named
mcpServersmap. This shape is useful for clients that manage multiple MCP servers in one config object. - Streamable HTTP: use this when the client expects one server transport object with
transport: "streamable_http". This shape describes the HTTP MCP transport directly.
Both shapes use the same endpoint and bearer token:
{
"mcpServers": {
"cyime-workspace": {
"type": "http",
"url": "http://127.0.0.1:8080/api/v1/mcp",
"headers": {
"Authorization": "Bearer <CYIME_API_TOKEN>"
}
}
}
}
{
"transport": "streamable_http",
"url": "http://127.0.0.1:8080/api/v1/mcp",
"headers": {
"Authorization": "Bearer <CYIME_API_TOKEN>"
},
"timeout": 5,
"sse_read_timeout": 300
}
Browser OAuth Token Flow
When the client supports browser OAuth, use the OAuth 2.0 authorization-code flow with PKCE:
- Authorization URL:
http://127.0.0.1:8080/api/v1/auth/skill/oauth/authorize - Token URL:
http://127.0.0.1:8080/api/v1/auth/skill/oauth/token - Response type:
code - Token grant type:
authorization_code - Recommended scopes:
workspace:read,workspace:write,document:read,document:write,file:move,file:copy - Optional destructive scope:
file:delete. Request it only when the user wants AI clients to move files to trash.
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.
- 9d ago First seen · 209 lines · 38 tokens per session scan A 00c036ba4bf6
cyime-workspace is a skill published in the GitHub repository Coldin04/Cyime (22 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,368 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
notion-cli
Work with Notion from the terminal using the notion CLI. Use when the user needs to read, create, update, query, or manage Notion pages, databases, blocks, comments, users, or files programmatically. Covers the entire Notion API with 50+ commands. Triggers: Notion workspace automation, database queries, page creation…
kb-import
Agent-guided procedure to import an existing non-OKF wiki or knowledge base (Obsidian vault, markdown folder, wiki export) into a Cartographer KB, incrementally and without big-bang LLM rewriting.
pkup-gen
Generate a PKUP report for given GitHub users. Use when the user asks to generate a PKUP report.
save-plan
Use when the user wants to save, export, or persist a plan (or any diagram-rich design doc shown in the CLI) to a markdown file so it can be opened and viewed with rendered mermaid diagrams. The terminal can't render mermaid; this writes the plan to docs/work/ /plans/ (or a temp scratch file) for viewing in an IDE…
review-design
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.
document
After implementing a new feature or fixing a bug, make sure to document the changes. Use when writing documentation, after finishing the implementation phase for a feature or a bug-fix.