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 provisiongit 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/provision)<a href="https://agentmods.dev/skills/aotter/mantle/provision"><img src="https://agentmods.dev/badge/skills/aotter/mantle/provision/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/provision"><img src="https://agentmods.dev/badge/skills/aotter/mantle/provision.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 | $0.00042 | $0.00568 |
| Opus 5.5 | $0.00017 | $0.00227 |
| Sonnet 5.5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
provision 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provision a Mantle project
Workflow
Read the installed SDK README, then follow the version-matched project and CLI workflow before editing.
Deploy/create resources only within the user's authorization; reuse configured
host resources. Apply reviewed and rehearsed migrations before routing traffic;
imports/first requests perform no DDL or schema checks. Keep auth dynamic, production
secrets in the host store, trusted HTTPS origin and verified bootstrap rule,
production email and selected media wiring. Configure Admin ASSETS worker-first
as in Workers assets and secrets. Hyperdrive caching stays off; PG settings are deployment-owned.
Keep the Workers public-fetch flags,
including environment overrides; verify deployed MCP with a real OAuth bearer
(initialize and tools/list), not only a browser session cookie.
For MCP Apps, also follow deployed host acceptance:
compare the current resource URI and visibly verify a newly invoked render tool.
Archive deployed Admin pages using the guide's previous recipe and carry them
through clean builds. Test the same old conversation after changing the UI build,
without reconnecting, refreshing host tools or clearing caches. A deliberate tool
contract change has its own migration/host rediscovery step. OAuth renewal, tools/call success and a
local official-host replay do not establish that the deployed App rendered.
Bun uses native Database/SQL, an app server and scheduler. Verify admin sign-in
(role admin), denied access, public reads, a persisted write, MCP and selected UI.
Report artifact/resources/checks and keep rollback artifacts.
For ChatGPT Sites, follow Mantle on ChatGPT Sites.
The app builds Admin with mantle bundle; serve it as Native
Admin describes. Verify both member and
admin OTP/UI flows. Deployment of an authorized application does not authorize
SDK publication; a workspace preview remains a preview.
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 Changed · -57 lines dc1d4a3b67fa
- 14d ago Changed · -93 lines · +10 tokens per session 191ab8fa64f6
- 27d ago Changed 8ed9b3b2ffbf
- 28d ago Changed · +10 lines 638da0ed7b48
- 1mo ago Changed · +6 lines · +6 tokens per session c5eaa4626dd7
- 1mo ago Changed · +10 lines · -33 tokens per session e2a84fde8a7d
- 1mo ago Changed 6f30fd967777
- 1mo ago Changed · +1 lines dcf4c03af166
- 1mo ago First seen · 168 lines · 59 tokens per session scan A cc1e5c9f2695
provision is a skill published in the GitHub repository aotter/mantle (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 568 once invoked, about $0.0002 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
cdn-fallback
Put a 3x-ui inbound behind a CDN (WebSocket, gRPC or xhttp through Cloudflare) or share port 443 between several inbounds using Xray fallbacks. Use when REALITY is blocked or unsuitable, when the server IP must stay hidden behind a CDN, when a real domain and certificate are in play, or when several protocols need to…
multi-node
Attach, secure and operate additional 3x-ui panels as nodes of a master panel — probe before saving, choose a TLS trust mode (verify/skip/pin/mTLS), select which inbounds sync, and monitor health and per-node traffic. Use when asked to add a server to a cluster, set up mTLS between panels, work out which node is…
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, restricting node access with IP or origin allowlists, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack…
deployment-completeness-audit
Read-only audit of changes that were built but not wired, deployed or exercised. Trace the target project's actual release path, runtime, migrations and adapters; report evidence and missing access honestly.
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.
acronis
The first real CLI for the Acronis Cyber Protect Cloud platform - every tenant, agent, and usage metric mirrored locally, with cross-tenant rollups no single API call returns. Trigger phrases: acronis backup health across tenants, find offline acronis agents, acronis usage and billing report, which acronis customers…