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 aotter/mantle --skill performancegit clone --depth 1 https://github.com/aotter/mantleWrote 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/aotter/mantle/performance)<a href="https://agentmods.dev/skills/aotter/mantle/performance"><img src="https://agentmods.dev/badge/skills/aotter/mantle/performance/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/aotter/mantle/performance"><img src="https://agentmods.dev/badge/skills/aotter/mantle/performance.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 | $0.02044 |
| Opus 5.5 | $0.00026 | $0.00818 |
| Sonnet 5.5 | $0.00013 | $0.00409 |
| Haiku 4.5 | $0.00007 | $0.00204 |
Grade A, and why
performance 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 yesterday.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mantle Performance
This skill sets direction: when to run, what to aim for, in what order and when to stop. It names no tools or commands. Choose the measurement and repair methods that fit the application, its host and the tools available to you; the targets and rules below are what stay fixed.
When to run
- After acceptance. Once independent acceptance reports CONVERGED for a new application or a feature, continue here before reporting done. Never optimize behavior that has not been accepted: after BLOCKED or UNVERIFIED, report that and stop.
- On request. When a user reports a slow page, slow first request or slow query, run only the part that covers it, then check the others it could affect.
Choose what to run
Decide from the manifests, the service entry and the changed files, not from guesses about future use. Run every part whose condition holds; record each skipped part with its reason.
| Run | When the application or change has | Skip when |
|---|---|---|
| Front end | Pages a browser opens directly that the application authors: public pages, member pages, a custom frontend, Admin customisations | The only browser UI is SDK-built Admin, unchanged; MCP and REST alone have no page to measure |
| Cold start | A deployed Worker or service entry: always for a new application; for a change, any added or moved import in the entry, its startup graph, a page's or an MCP App entry's first-load code | The change touched no import, entry, page or MCP App bundle |
| Backend reads | Views, or Store reads in handlers, whose rows grow with data: lists, search, paging, joins, aggregates, totals, reports | Only id lookups and small, bounded configuration tables |
| Backend writes | Procedures or Store writes that run often or concurrently: stock, counters, approvals, checkout, imports | Rare single-row administrative writes |
A change in one part can move another: an added index slows writes, a shared stylesheet or entry import affects every page. Re-measure what a repair can reach.
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.
- yesterday First seen · 149 lines · 66 tokens per session scan A cddbf33d71f4
performance is a skill published in the GitHub repository aotter/mantle (5 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 2,044 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 2026-10-24.
Other skills, from other repositories
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
user-usecases
Database of real user use cases for APIbase platform. Contains detailed examples of how specific APIs are onboarded, wrapped, and served to AI agents. Use this skill when you need to reference real integration examples, explain the APIbase onboarding process, or design new API wrappers based on proven patterns.
diagnose-connectivity
Work out why a 3x-ui client cannot connect, in the order that finds the cause fastest — scope the outage, check the core, the inbound, the client's own limits, routing and outbounds, then the node. Use whenever someone reports "it stopped working", a client cannot connect, a site is unreachable through the proxy, or…
blazemeter-api-monitoring
Comprehensive guide for BlazeMeter API Monitoring, including test creation, configuration, scripting, integrations, notifications, and management. Use when working with API Monitoring tests for (1) Creating and configuring API tests, (2) Writing custom scripts (Initial, Pre-request, Post-response), (3) Integrating…
spotify-exhaustive-feature-sweep
Exhaustive feature sweep across Spotify domains — enumerate all endpoints into quantity-first tool proposals with quota flags and batched GitHub logging.
aurora-backend-setup
Set up, build, or troubleshoot the AURORA Agent (bioprism) MCP server used by the aurora-backend plugin. Use when the aurora-agent MCP server fails to start, when its tools are missing from a session, when asked to install or build the aurora-agent backend, or when a bioprism build or test behaves strangely on Windows.