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 agentmods add skills/fxckcode/mcp-cor/cor-authnpx skills add fxckcode/mcp-cor --skill cor-authgit clone --depth 1 https://github.com/fxckcode/mcp-corWhat 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 | $0.00036 | $0.02406 |
| Opus 5 | $0.00018 | $0.01203 |
| Sonnet 5 | $0.00007 | $0.00481 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
cor-auth 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 yesterday.
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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COR Auth — Cheat Sheet
Overview
The COR MCP Server supports two authentication modes with auto-detection. The server checks env vars at startup and picks the right flow automatically.
| Mode | Env Vars | Use Case |
|---|---|---|
| User Credentials | COR_EMAIL + COR_PASSWORD |
Personal use, testing, single-user agents |
| Client Credentials | COR_API_KEY + COR_CLIENT_SECRET |
Server-to-server, automated workflows |
Priority: User Credentials (email/password) takes priority when both are set. To use Client Credentials, leave email/password unset.
Mode A: User Credentials (Email + Password)
Step-by-Step
-
Set environment variables:
[email protected] COR_PASSWORD=your_secret_password COR_API_URL=https://api.projectcor.com/v1 -
Server detects auth mode →
"Auth mode: User Credentials (email/password)" -
On first API call, the server sends:
POST https://api.projectcor.com/v1/auth/login Content-Type: application/x-www-form-urlencoded Accept: application/json [email protected]&password=your_secret_password -
COR API responds with one of these shapes:
// Shape 1 — direct token {"access_token": "eyJ...", "expires_in": 3600} // Shape 2 — nested token object {"token": { "access_token": "eyJ...", "type": "bearer", "refreshToken": "rt_...", "expirationTime": "1712345678000" }} // Shape 3 — data wrapper {"data": {"token": "eyJ..."}} -
Token is cached in the
TokenStore(thread-safe, in-memory). -
Subsequent API calls reuse the cached token until it's within 60 seconds of expiry, then auto-refresh.
Email/Password Auth Flow Diagram
┌─────────┐ ┌──────────────┐ ┌──────────────┐
│ Hermes │ tool │ COR MCP │ POST │ COR API │
│ Agent │────────►│ Server │─────────►│ /auth/login │
│ │ │ │◄─────────┤ │
│ │ │ TokenStore │ JWT │ │
│ │ │ cache │ └──────────────┘
└─────────┘ └──────────────┘
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.
- yesterday First seen · 274 lines · 36 tokens per session scan A fc20d8f1c147
cor-auth is a skill published in the GitHub repository fxckcode/mcp-cor (0 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,406 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 2026-08-31.
Other skills, from other repositories
plane-workflow
Create, update, audit, standardize, label, and organize Plane work items with the Plane Workflow MCP tools. Use when a user asks to create a Plane task or issue, turn a brief into a ticket, manage modules, or improve a Plane backlog.
agile-development
ServiceNow Agile Development 2.0 — the rmteam → rmsprint → rmstory → rmepic model, the state and point values ServiceNow actually accepts, how a story is attached to a sprint, and the reporting tools (board, burndown, velocity, capacity, standup, retrospective).
linear-oneshot
Find one-shottable WaniWani Linear tickets and scope them for autonomous execution. Use when the user says "triage one-shots", "find easy tickets", "find simple tickets", "one-shot triage", "qualify WAN-123", "scope WAN-123", "is this ticket one-shottable", or wants to label simple Linear tickets an agent can…
discover-work
Deep research across codebase, GitHub issues, discussions, project board, and architecture docs to discover new tasks, gaps, technical debt, and improvement ideas. Trigger when user says: discover work, find tasks, what needs doing, audit codebase, find gaps, technical debt audit, backlog discovery, brainstorm tasks…
building-glamorous-tuis
Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.
ulc-loop
Start a Unified Loop Controller session via Ralph Wiggum. Autonomously works through backlog, dispatches agents, and explores via QD when idle.