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 Tulimoa/tulimoa-mcp --skill tulimoa-gatewaygit clone --depth 1 https://github.com/Tulimoa/tulimoa-mcpWrote 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/tulimoa/tulimoa-mcp/tulimoa-gateway)<a href="https://agentmods.dev/skills/tulimoa/tulimoa-mcp/tulimoa-gateway"><img src="https://agentmods.dev/badge/skills/tulimoa/tulimoa-mcp/tulimoa-gateway/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/tulimoa/tulimoa-mcp/tulimoa-gateway"><img src="https://agentmods.dev/badge/skills/tulimoa/tulimoa-mcp/tulimoa-gateway.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 | $0.00066 | $0.00750 |
| Opus 5 | $0.00033 | $0.00375 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
tulimoa-gateway 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 11d 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.
What it actually says
Use this skill when an agent should reach several SaaS tools through a single MCP endpoint AND keep working memory that survives context compaction and new sessions.
It connects to the Tulimoa gateway (remote) at https://gateway.tulimoa.com/mcp. The gateway federates the tools you connect in the Tulimoa dashboard (the Tulimoa directory is always available; other SaaS appear once connected) and adds a memory layer on top. Reading memory needs a read-scoped key; writing/deleting needs a write-scoped key. The gateway advertises its authorization server via RFC 9728 discovery, so a compliant client can run the OAuth flow, or you can pass a Tulimoa gateway API key as a Bearer token.
The memory is what keeps the agent from forgetting. Native memory tools (namespaced tulimoa__):
recall— pull back what was established earlier (pinned facts, IDs, decisions, open loops). Call at the START of a task and again before finishing. Args:topic(optional free-text filter),limit.remember— store a durable fact (an ID, a decision, a preference, a resource you will reuse). Args:text, optionalkey(a stable key overwrites the previous value for that key — no duplicate facts),importance,durable(keep across sessions),share_with_team. Credential-shaped text is refused; store a reference instead.set_goal— set the one active goal for the session; resurfaced if context is compacted.checkpoint— save a plan before a multi-step, multi-tool task so it can be resumed after compaction.forget— remove a remembered item byidorkey.get_pending— replay events missed while disconnected or after compaction.recall_result— fetch the full payload of an earlier tool result that the gateway replaced with a short dedup pointer (pass thecache_keyfrom the[tulimoa dedup]note).
Behaviour worth knowing:
- The gateway injects a compact continuity block into tool results when it matters (goal changed, a new ID was captured, the agent looks disoriented), so the working context travels with the conversation instead of being lost.
- Byte-identical repeated tool calls are collapsed to a short pointer to save tokens; the full payload stays retrievable via
recall_result. Structured output is passed through unchanged. - Memory is EU-hosted. A user can export or erase all of their gateway memory (GDPR Art. 15 / 17) from the Tulimoa dashboard; an erase clears live sessions within seconds.
Guidance: at the start of a task call tulimoa__recall to load prior context; whenever you learn something durable (an ID, a decision, a user preference) call tulimoa__remember; for a multi-step plan call tulimoa__set_goal / tulimoa__checkpoint; before finishing, tulimoa__recall once more so you do not drop an open loop.
What ships with it
1 file 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.
- 11d ago First seen · 29 lines · 66 tokens per session scan A 558efa178490
tulimoa-gateway is a skill published in the GitHub repository Tulimoa/tulimoa-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 750 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.