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 RagavRida/agentsmcp --skill antigravitygit clone --depth 1 https://github.com/RagavRida/agentsmcpWrote 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/ragavrida/agentsmcp/antigravity)<a href="https://agentmods.dev/skills/ragavrida/agentsmcp/antigravity"><img src="https://agentmods.dev/badge/skills/ragavrida/agentsmcp/antigravity/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/ragavrida/agentsmcp/antigravity"><img src="https://agentmods.dev/badge/skills/ragavrida/agentsmcp/antigravity.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 | $0.00075 | $0.02326 |
| Opus 5.5 | $0.00030 | $0.00930 |
| Sonnet 5.5 | $0.00015 | $0.00465 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade A, and why
agentmailbox 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 1mo 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentMailbox — Context Sync for AI Agents
Every agent has a mailbox. No agent ever starts cold.
AgentMailbox is a context-sync protocol that gives you durable, persistent threads across sessions, tools, and restarts. When you receive a message, you get the full thread state — snapshot, structured summary, recent messages — so you can pick up exactly where the last agent (or the last session) left off.
When to Use This Skill
- Session start: Check your mailbox for context from previous sessions
- "What was I working on?": Receive and sync threads to restore context
- Multi-agent tasks: Send messages to other agents, coordinate via threads
- Before switching tools: Send a summary so the next tool picks up seamlessly
- After completing work: Record decisions, artifacts, and progress to the thread
- Cross-platform continuity: Context follows the user across Cursor, Claude Desktop, Antigravity, Continue, and any MCP client
RULE #1: Memory First — ALWAYS
When a user gives you ANY query or task:
- IMMEDIATELY call
agentsmcp_context_briefingwith the user's query as thetaskparameter - Read the returned briefing — it contains relevant files, symbols, decisions, tasks, and relationships from persistent memory
- If the briefing returns results, USE THEM as your starting context instead of reading raw files
- Only fall back to
grep/view_file/read_filewhen the briefing returns empty results
Context Lookup Priority (use in order)
agentsmcp_context_briefing— one-shot task briefing (graph + index combined)agentsmcp_get_index— look up a specific file/symbol by key (~200 tokens vs full file)agentsmcp_search_index— keyword search across all indexed entries (replaces grep)agentsmcp_query_graph— relationship traversal (find connected files/symbols/decisions)- LAST RESORT:
grep/view_file— only when memory has no entry
Setup
Quick Setup (MCP)
AgentMailbox works via MCP. Add this to your MCP configuration:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 267 lines · 75 tokens per session scan A d8aec4414704
agentmailbox is a skill published in the GitHub repository RagavRida/agentsmcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 2,326 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 2026-08-31.
Other skills, from other repositories
wiki-ingest
Use when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest ". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
wiki-lint
Use when an LLM Wiki operation issue is a lint or health check. Audit for contradictions, orphans, weak provenance, broken links, missing concept pages, and index/log drift; return triage findings without auto-fixing.
claude-compaction-restore
Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compact, or must rebuild its working picture of a long-running seat from its own restore map, its JSONL transcript and the files it touched.
retiring-and-inheriting-a-seat
Use when you are a sitting agent near your context threshold (85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure)…
cao-learning
Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…
memory
Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…