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 rules/bigdata2211it-web/ai-skills-map/skills-mapgit clone --depth 1 https://github.com/bigdata2211it-web/ai-skills-mapWrote 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/rules/bigdata2211it-web/ai-skills-map/skills-map)<a href="https://agentmods.dev/rules/bigdata2211it-web/ai-skills-map/skills-map"><img src="https://agentmods.dev/badge/rules/bigdata2211it-web/ai-skills-map/skills-map.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00751 |
| Opus 5 | $0.00030 | $0.00376 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
skills-map 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.
| droid-byok | https://github.com/bigdata2211it-web/ai-droid-skills | Use any custom BYOK (bring-your-own-key) OpenAI-compatible model with Factory.ai's `droid` CLI without a Factory account: bypass the platform auth gat How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skills-map — index of AI agent skills
Goal
A short map of every AI agent skill published under GitHub user
bigdata2211it-web. For each skill: a link to its GitHub repo and a
one-line description of what it does. Use when the user asks "what
skills are there", "show me all skills", "give me the github link for
skill X", or when an agent needs to know which skill covers a task.
Each skill is its own git repo — clone the one you need.
Map
| Skill | GitHub repo | What it does |
|---|---|---|
| mybd-cryfs | https://github.com/bigdata2211it-web/ai-vault-skills | Encrypted credentials vault with cryfs (FUSE): cross-platform install, migration, daily open/close, auto-lock, agent discipline, backup, password change, troubleshooting. |
| wine-exe-fix | https://github.com/bigdata2211it-web/ai-wine-skills | Diagnose and fix Windows .exe launch failures under Wine: 32/64-bit prefix, .NET runtime, missing NuGet DLLs, assembly vs package version, binding redirects, DirectX, fonts, VC++ runtimes, MSI/COM/registry fixes, .desktop launchers. |
| droid-byok | https://github.com/bigdata2211it-web/ai-droid-skills | Use any custom BYOK (bring-your-own-key) OpenAI-compatible model with Factory.ai's droid CLI without a Factory account: bypass the platform auth gate via FACTORY_AIRGAP_ENABLED=1, literal provider key in ~/.factory/settings.json instead of fragile ${VAR} substitution, persistent airgap for shells/GUI/cron/daemon, curl endpoint validation, E2E verification with a negative test, 401/402/404 BYOK troubleshooting. Provider-agnostic (OpenRouter, Ollama, LM Studio, vLLM, Azure OpenAI, Groq, Together, DeepSeek, FreeModel). |
| freemodel-cc-proxy | https://github.com/bigdata2211it-web/ai-freemodel-cc-proxy-skill | Real Claude (Opus/Sonnet/Haiku) from FreeModel cc.freemodel.dev for any Anthropic client (Factory Droid, Claude Code, Cline, Cursor, Pi CLI, Anthropic SDK): reverse-engineer the client-fingerprint gate (body shape, not TLS/key) via mitmproxy, build a Node proxy that injects it, wire into Droid (provider:anthropic+FACTORY_AIRGAP_ENABLED=1)/Pi (~/.pi/agent/models.json)/SDK, systemd autostart, web UI, troubleshooting 403/401. Companion proxy code: ai-freemodel-cc-proxy. |
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 · 37 lines · 60 tokens per session scan A d4f397c23567
skills-map is a cursor rule published in the GitHub repository bigdata2211it-web/ai-skills-map (2 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 751 once invoked, about $0.0003 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.