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 uwuclxdy/agenticat --skill mcp-statelessgit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/mcp-stateless)<a href="https://agentmods.dev/skills/uwuclxdy/agenticat/mcp-stateless"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/mcp-stateless/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/uwuclxdy/agenticat/mcp-stateless"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/mcp-stateless.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 | $0.00022 | $0.02079 |
| Opus 5 | $0.00011 | $0.01040 |
| Sonnet 5 | $0.00004 | $0.00416 |
| Haiku 4.5 | $0.00002 | $0.00208 |
Grade A, and why
mcp-stateless 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 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Stateless
The Model Context Protocol went stateless in revision 2026-07-28. It is the largest break since launch: the initialize handshake, the session id, the standalone SSE stream, and server-initiated requests are all gone. Every request now carries everything a server needs to answer it.
Model training data predates this revision. An MCP server written from memory speaks the 2025-11-25 protocol and will be rejected by a modern client. The failure is not a compile error and often not a runtime error either: a handshake-era server and a modern client fail in ways that read like a config problem. Work from the reference files here, and check anything version-sensitive against the live spec.
Hard Rules
- Never write MCP wire code from memory. Read
references/wire.mdfirst. If a claim here is older than the revision you are targeting, the live spec wins. - State is a lie the connection tells you. A server MUST NOT infer anything from a previous request on the same connection: not the protocol version, not capabilities, not client identity, not conversation continuity. One stdio process is not one session. A client may interleave unrelated requests on it.
- State that must span requests gets an explicit server-minted handle passed back as an ordinary parameter. There is no session to hang it on.
- A server MUST answer
server/discover. It is the only way left to advertise what the server supports, and it is how a dual-era client tells a modern server from a legacy one. - Every result carries
resultType. Omitting it marks the server as legacy. A result with noresultTypeMUST be read as"complete". - Servers never send JSON-RPC requests. Sampling, elicitation, and roots all run through multi round-trip requests: the server answers with
input_required, the client retries. Readreferences/mrtr.mdbefore wiring any of the three. requestStatecomes back from the client unverified. Sign or encrypt it. A stateless server that trusts an echoed blob has handed the client its internal state machine.- Verify with a live handshake against the real binary. A green build proves nothing about protocol conformance, and the old smoke-test recipe (pipe an
initializeframe) now tests a method that no longer exists. Recipe inreferences/sdks.md.
What ships with it
4 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.
- 9d ago First seen · 91 lines · 22 tokens per session scan A c9780333368e
mcp-stateless is a skill published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,079 once invoked, about $0.0001 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
meta-harness
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…
meta-harness-proteus
Run one iteration of proteus memory-summary evolution. Called by metaharness.py.
gbg
Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".