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 1508550385junnan-bot/Magic-Agent-Global-Rules --skill global-collaboration-rulesgit clone --depth 1 https://github.com/1508550385junnan-bot/Magic-Agent-Global-RulesWrote 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/1508550385junnan-bot/magic-agent-global-rules/global-collaboration-rules)<a href="https://agentmods.dev/skills/1508550385junnan-bot/magic-agent-global-rules/global-collaboration-rules"><img src="https://agentmods.dev/badge/skills/1508550385junnan-bot/magic-agent-global-rules/global-collaboration-rules/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/1508550385junnan-bot/magic-agent-global-rules/global-collaboration-rules"><img src="https://agentmods.dev/badge/skills/1508550385junnan-bot/magic-agent-global-rules/global-collaboration-rules.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 | $0.00108 | $0.01309 |
| Opus 5 | $0.00054 | $0.00655 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
global-collaboration-rules 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Before complex tasks: search local skills → search online (skills.sh, GitHub, known repos: mxyhi/ok-skills, obra/superpowers, LearnPrompt/cc-harness-skills) → compare multiple → pick best. Use Python urllib, not curl/git The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 123 lines · 108 tokens per session scan A b2a9f00c9ae3
global-collaboration-rules is a skill published in the GitHub repository 1508550385junnan-bot/Magic-Agent-Global-Rules (2 stars, last pushed 3mo ago), licensed GPL-3.0. It adds 108 tokens to every session and 1,309 once invoked, about $0.0005 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 skills, from other repositories
entroly-evidence-operations
Use Entroly for content-blind agent-history audits, explicit baseline/optimized trials, recoverable command or browser evidence, response contracts, and token-efficiency claim verification.
cached-system-instructions
How to structure hierarchical, immutable system instructions to maximize KV-cache hits on Anthropic and OpenAI, slashing Time-to-First-Token (TTFT) by 80% and input costs by 90%.
avoid-duplicate-system-messages
How to consolidate fragmented system instructions into a single static cacheable header, maximizing Anthropic and OpenAI prompt cache hit rates and cutting input token costs by 90%.
authoring-skills-and-rules
Author Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation model, cross-platform mirroring, and the universal craft: progressive disclosure, trigger-rich descriptions (context pointers), leading words, token budget…
zipai-optimizer
Skill "zipai-optimizer" from nickdesi/ZipAI, covering zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
cache-guard
Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user…